Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicant’s amendment filed on 7/7/2025 has been entered. Claims 1, 3, 8, 12 and 17 have been amended, and no claims have been canceled or added.
Applicant’s arguments with respect to claims 1, 12 and 17 under 35 USC 102(a)(1) as being anticipated by Garg et al (US 20230366983 A1), hereinafter Garg has been fully considered and are not persuasive. The Applicant asserts that Garg fails to disclose the following:
Regarding claim 1 Garg fails to disclose:
the reflective-intensity data containing multiple spatially invariant spectrums; however, Garg discloses: the reflective-intensity data containing multiple spatially invariant spectrums (Garg, para [0070], FIG. 5A is a diagram illustrating an example polar grid 500 in accordance with aspects of the present disclosure. A transmitter (e.g., an array of transmit antennas) of a radar 502 may transmit pulses of electromagnetic radio frequency (RF) waves. The transmitted RF waves may be reflected from one or more objects encountered in the transmission path. The object may, for example, be a vehicle, a person, a building structure, or other object. A portion of the electromagnetic RF waves that are reflected from the objects may be returned to a receiver (e.g., an array of receive antennas) of the radar 502) Examiner notes that reflective intensity data is from far and the multiple spatially invariant spectrums may include parked vehicles, buildings, etc.
generating a reflective intensity volume (RIV) based on the reflective intensity data; however, Garg discloses: generating a reflective intensity volume (RIV) based on the reflective intensity data (Garg, para [0070]) Examiner notes that reflective intensity volume data includes walls a building, surfaces of vehicles i.e. hood, windows, sides, etc.;
applying a trained convolutional neural network (CNN) on the generated RVI; however, Garg discloses: applying a trained convolutional neural network (CNN) on the generated RVI (Garg, para [0042], One type of convolutional neural network is a deep convolutional network (DCN). FIG. 2D illustrates a detailed example of a DCN 200 designed to recognize visual features from an image 226 input from an image capturing device 230, such as a car-mounted camera. The DCN 200 of the current example may be trained to identify traffic signs and a number provided on the traffic sign. Of course, the DCN 200 may be trained for other tasks, such as identifying lane markings or identifying traffic lights).
Regarding claim 9, the Applicant asserts that Garg fails to disclose:
Converting the three-dimensional, spatially invariant range-speed-adjusted azimuth transform into a three-dimensional, spatially variant range-speed-azimuth transform by performing inverse sine operation in the azimuth spectrum; however, Garg discloses: wherein the applying includes converting the three-dimensional, spatially invariant range-speed-adjusted azimuth transform into a three-dimensional, spatially variant range-speed-azimuth transform by performing inverse sine operation in the azimuth spectrum (Garg, para [0064], A set of features of the radar ping or return signal may be extracted. For instance, the features may be extracted by subjecting the input to one or more convolutional layers (e.g., element 356 shown in FIG. 3). The input features may, for example, include coordinates (e.g., polar coordinates or Cartesian coordinates) of the ping or detection resolved along the radar's axis, a longitudinal component of relative velocity estimated from Doppler measurement as Doppler/cosine (azimuth angle measured with respect to the forward direction), a radar cross-section (RCS) of the ping or detection or sine of the azimuth angle of the ping or detection. Additionally, in some aspects, global frame level features, such as the density of points near a ping or detection may be used to determine whether an edge exists between two nodes, thus indicating that the corresponding pings are from the same object) Examiner notes that conversion of three-dimension is fundamental to range, speed, Doppler and azimuth. Additionally, the conversion of polar to Cartesian is an example of radar detections from the neural network grid (that of CNN to detect pedestrians, vehicles, etc.) into real-world positions (i.e. speed) of which are core to tracking and motion planning
Regarding claim 10, the Applicant asserts that Garg fails to disclose:
The RIV includes reflection points and has matching spreading functions associated with each reflection point. However, Garg discloses: wherein the RIV includes reflection points and has matching spreading functions associated with each reflection point (Garg, para [0071], In an aspect, the radar 502 may be an imaging radar that uses beamforming to scan horizontally and vertically. Beamforming is a technique used to aim the effective direction of a radar beam by changing the delay between different transmitting antennas so that the signals add constructively in a specified direction. As such, the radar 502 may scan horizontally and vertically across the sensing area by using a transmitter that includes an array of electronically steered antennas (not shown). The radar 502 may be positioned at a fixed location or may be mobile (e.g., coupled to a vehicle) Examiner notes that fixed targets at a known location are examples of reflective information with a matching spread function
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-10 and 12-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Garg et al (US 20230366983 A1), hereinafter Garg.
Regarding claim 1, Garg discloses:
a method that facilitates object detection, the method comprising (Garg, Abstract, A processor-implemented method for radar-based tracking of an object includes transmitting radio frequency (RF) signals. In response to the transmitted RF signals, one or more return RF signals are received. Features of the one or more return RF signals are extracted. A graph comprising multiple nodes is generated. Each node of the graph corresponds to the one or more return RF signals and indicates a potential target object detection. An existence of a plurality of edges is determined. Each edge connects a pair of nodes in the graph based on features of the return RF signals. The existence of each edge indicates that the pair of nodes connected correspond to a same target object):
obtaining reflective radar signals regarding a scene monitored (Garg, Abstract),
the reflective radar signals being received by multiple antennas of a radar sensor system (Garg, para [0070], FIG. 5A is a diagram illustrating an example polar grid 500 in accordance with aspects of the present disclosure. A transmitter (e.g., an array of transmit antennas) of a radar 502 may transmit pulses of electromagnetic radio frequency (RF) waves. The transmitted RF waves may be reflected from one or more objects encountered in the transmission path. The object may, for example, be a vehicle, a person, a building structure, or other object. A portion of the electromagnetic RF waves that are reflected from the objects may be returned to a receiver (e.g., an array of receive antennas) of the radar 502);
producing reflective-intensity data based on the reflective radar signals (Garg, paras [0070] and [0072, The returned responses (radar returns or pings) measured by the radar 502 may be characterized as the polar grid 500 having observation cells 506. Each cell 506 represents the measured returned response value at a specific range (r) and angle/azimuth (0). Each cell 506 is alternately referred to as a range-angle bin. Features 508a-c (e.g., a returned response) may be extracted from the cells 506 to determine whether the feature 508a-c are an indication of an object. Each feature (e.g., 508a-c) within a respective cell 506 may be identified as having parameters such as range, Doppler measurement, azimuth, and elevation. As an example, a feature 508 within a cell 506 may be the signal-to-noise ratio (SNR) computed by a constant false alarm rate (CFAR) algorithm. However, it should be understood that other methods may be used to target and identify features 508 within a cell 506),
the reflective- intensity data containing multiple spatially invariant spectrums (Garg, para [0070]) Examiner notes that reflective intensity data is from far and the multiple spatially invariant spectrums may include parked vehicles, buildings, etc.;
generating a reflective intensity volume (RIV) based on the reflective-intensity data (Garg, para [0070]) Examiner notes that reflective intensity volume data includes walls a building, surfaces of vehicles i.e. hood, windows, sides, etc;
applying a trained convolutional neural network (CNN) on the generated RIV (Garg, para [0042], One type of convolutional neural network is a deep convolutional network (DCN). FIG. 2D illustrates a detailed example of a DCN 200 designed to recognize visual features from an image 226 input from an image capturing device 230, such as a car-mounted camera. The DCN 200 of the current example may be trained to identify traffic signs and a number provided on the traffic sign. Of course, the DCN 200 may be trained for other tasks, such as identifying lane markings or identifying traffic lights);
and detecting objects in the scene based, at least in part, the applying of the trained CNN on the generated RIV (Garg, para [0042]).
Regarding claim 2, Garg discloses:
a method of claim 1 further comprising (Garg, Abstract and para [0070]):
reporting detected objects to a perception system of a vehicle (Garg, para [0070]);
and classifying the detected objects in the scene (Garg, para [0080], FIG. 7 is a flow diagram illustrating a method 700 for training a classifier for radar clustering via an artificial neural network, in accordance with aspects of the present disclosure. The method may be implemented by a processor, for example. As shown in FIG. 7, at block 702, the method 700 receives a dataset including one or more radar detections associated with an identification of a ground truth object that produced each of the one or more radar detections).
Regarding claim 3, Garg discloses:
a method of claim 1 (Garg, Abstract and para [0070]),
wherein the spatially invariant spectrums of the reflective-intensity data include (Garg, para [0070])
1) a range reflective-intensity spectrum includes relative distances between reflection points indicated by the reflective-intensity data and the radar sensor system (Garg, paras [0070] and [0072]),
2) a speed ("Doppler") reflective-intensity spectrum includes speeds of the reflection points indicated by the reflective- intensity data relative to the radar sensor system (Garg, paras [0070] and [0072]),
and 3) an adjusted azimuth ("adjusted-azimuth") spectrum, which is based on azimuths of the reflection points indicated by the reflective-intensity data relative to the radar sensor system (Garg, paras [0070] and [0072]).
Regarding claim 4, Garg discloses:
a method of claim 3 (Garg, Abstract and para [0070]),
wherein the producing reflective-intensity data includes determining a two-dimensional range-Doppler transform that incorporates the range reflective-intensity spectrum and Doppler reflective-intensity spectrum (Garg, para [0052], e processing of each layer of a convolutional network may be considered a spatially invariant template or basis projection. If the input is first decomposed into multiple channels, such as the red, green, and blue channels of a color image, then the convolutional network trained on that input may be considered three-dimensional, with two spatial dimensions along the axis of the image and a third dimension capturing color information. The outputs of the convolutional connections may be considered to form a feature map in the subsequent layer, with each element of the feature map (e.g., 220) receiving input from a range of neurons in the previous layer (e.g., feature maps 218) and from each of the multiple channels. The values in the feature map may be further processed with a non-linearity, such as a rectification, max(0, x). Values from adjacent neurons may be further pooled, which corresponds to down sampling, and may provide additional local invariance and dimensionality reduction. Normalization, which corresponds to whitening, may also be applied through lateral inhibition between neurons in the feature map.).
Regarding claim 5, Garg discloses:
a method of claim 4 (Garg, Abstract and para [0070]),
wherein the determining the two-dimensional range-Doppler transform includes (Garg, para [0052]):
transforming the range reflective-intensity spectrum by the reflective radar signals (Garg, paras [0052] and [0072]),
wherein the range reflective-intensity spectrum includes range bins based on the reflective radar signals by multiple antennas of the radar sensor system (Garg, paras [0070] and [0072]);
and transforming the Doppler reflective-intensity spectrum by the reflective radar signals (Garg, paras [0072] and [0074], FIG. 5B is a diagram illustrating an example graph 550 of radar clustering using an artificial neural network in accordance with aspects of the present disclosure. Referring to FIG. 5B, the features 508a-c are represented in the graph 550 as corresponding nodes 558a-c, respectively. Radar data for each of the nodes 558a-c may be analyzed, for example using a depth first search to determine whether the nodes (e.g., 558a-c) correspond to a same object. For instance, as shown in FIG. 5B, considering the radar data (e.g., Doppler measurements) corresponding to node 558b and node 558c, nodes 558b and 558c may be determined to be from a same object. Thus, an edge 552 is included in the graph 550 connecting node 558b and 558c. Conversely, considering the radar data (e.g., Doppler measurements) corresponding to node 558a and node 558b, nodes 558a and 558b may be determined to be from different objects),
wherein the Doppler reflective-intensity spectrum includes Doppler bins based on the range bins and the reflective radar signals by multiple antennas of the radar sensor system (Garg, para [0072]) Examiner notes that Doppler bins are fundamental to Doppler radar in that the radar data is grouped based upon frequency shift and correspond to velocity intervals.
Regarding claim 6, Garg discloses:
a method of claim 3 (Garg, Abstract and para [0070]),
wherein the producing reflective-intensity data includes determining the adjusted-azimuth spectrum by calculating sine of the azimuth ("sin(azimuth)") relative to a two-dimensional range-Doppler transform that incorporates the range reflective-intensity spectrum and Doppler reflective-intensity spectrum (Garg, paras [0052] and [0064], A set of features of the radar ping or return signal may be extracted. For instance, the features may be extracted by subjecting the input to one or more convolutional layers (e.g., element 356 shown in FIG. 3). The input features may, for example, include coordinates (e.g., polar coordinates or Cartesian coordinates) of the ping or detection resolved along the radar's axis, a longitudinal component of relative velocity estimated from Doppler measurement as Doppler/cosine (azimuth angle measured with respect to the forward direction), a radar cross-section (RCS) of the ping or detection or sine of the azimuth angle of the ping or detection. Additionally, in some aspects, global frame level features, such as the density of points near a ping or detection may be used to determine whether an edge exists between two nodes, thus indicating that the corresponding pings are from the same object).
Regarding claim 7, Garg discloses:
a method of claim 5, wherein (Garg, Abstract and para [0070]):
the producing reflective-intensity data includes determining the adjusted-azimuth spectrum by calculating sine of the azimuth ("sin(azimuth)") relative to the range bins and Doppler bins of the two-dimensional range-Doppler transform (Garg, paras [0052] and [0064]);
and the generating includes combining results of the calculating for the range bins and Doppler to produce a three-dimensional, spatially invariant range-speed-adjusted-azimuth transform (Garg, para [0052]).
Regarding claim 9, Garg discloses:
a method of claim 7 (Garg, Abstract and para [0070]),
wherein the applying includes converting the three-dimensional (Garg, para [0064], A set of features of the radar ping or return signal may be extracted. For instance, the features may be extracted by subjecting the input to one or more convolutional layers (e.g., element 356 shown in FIG. 3). The input features may, for example, include coordinates (e.g., polar coordinates or Cartesian coordinates) of the ping or detection resolved along the radar's axis, a longitudinal component of relative velocity estimated from Doppler measurement as Doppler/cosine (azimuth angle measured with respect to the forward direction), a radar cross-section (RCS) of the ping or detection or sine of the azimuth angle of the ping or detection. Additionally, in some aspects, global frame level features, such as the density of points near a ping or detection may be used to determine whether an edge exists between two nodes, thus indicating that the corresponding pings are from the same object) Examiner notes that conversion of three-dimension is fundamental to range, speed, Doppler and azimuth. Additionally, the conversion of polar to Cartesian is an example of radar detections from the neural network grid (that of CNN to detect pedestrians, vehicles, etc.) into real-world positions (i.e. speed) of which are core to tracking and motion planning
spatially invariant range-speed-adjusted-azimuth transform into a three-dimensional (Garg, para [0064]),
spatially variant range-speed-azimuth transform by performing inverse sine operation in the azimuth spectrum (Garg, para [0064]).
Regarding claim 10, Garg discloses:
a method of claim 7 (Garg, Abstract and para [0070]),
wherein the RIV includes reflection points and has matching spreading functions associated with each reflection point (Garg, para [0071], In an aspect, the radar 502 may be an imaging radar that uses beamforming to scan horizontally and vertically. Beamforming is a technique used to aim the effective direction of a radar beam by changing the delay between different transmitting antennas so that the signals add constructively in a specified direction. As such, the radar 502 may scan horizontally and vertically across the sensing area by using a transmitter that includes an array of electronically steered antennas (not shown). The radar 502 may be positioned at a fixed location or may be mobile (e.g., coupled to a vehicle) Examiner notes that fixed targets at a known location are examples of reflective information with a matching spread function
Regarding claim 12, Garg discloses:
a method comprising (Garg, Abstract and para [0070]):
obtaining reflective radar signals regarding a scene monitored (Garg, Abstract),
the reflective radar signals being received by multiple antennas of a radar sensor system (Garg, para [0070]);
producing reflective-intensity data based on the reflective radar signals (Garg, paras [0070] and [0072]),
the reflective- intensity data containing multiple spatially invariant spectrums, which include (Garg, paras [0070] and [0072])
1) a range reflective-intensity spectrum includes relative distances between reflection points indicated by the reflective-intensity data and the radar sensor system (Garg, para [0072]),
2) a speed ("Doppler") reflective-intensity spectrum includes speeds of the reflection points indicated by the reflective-intensity data relative to the radar sensor system (Garg, para [0072]),
and 3) an adjusted azimuth ("adjusted-azimuth") spectrum, which is based on azimuths of the reflection points indicated by the reflective-intensity data relative to the radar sensor system(Garg, para [0072]),
and wherein the producing includes determining a two-dimensional range- Doppler transform that incorporates the range reflective-intensity spectrum and Doppler reflective- intensity spectrum (Garg, para [0072]);
generating a reflective intensity volume (RIV) based on the reflective-intensity data(Garg, para [0072]));
applying a trained convolutional neural network (CNN) on the generated RIV (para [0072]);
and detecting objects in the scene based, at least in part, the applying of the trained CNN on the generated RIV (para [0042]).
Claim 13 is rejected under the same analysis as claim 5.
Claim 14 is rejected under the same analysis as claim 6.
Claim 15 is rejected under the same analysis as claim 7.
Claim 16 is rejected under the same analysis as claim 9.
Regarding claim 17, Garg discloses:
a non-transitory machine-readable storage medium encoded with instructions executable by one or more processors that (Garg, para [0145, col. 11 lines 6-16], Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Thus, in some aspects computer-readable media may comprise non-transitory computer-readable media (e.g., tangible media). In addition, for other aspects computer-readable media may comprise transitory computer-readable media (e.g., a signal). Combinations of the above should also be included within the scope of computer-readable media),
when executed, direct the one or more processors to perform operations that facilitate object detection, the operations comprising (Garg, para [0146], Thus, certain aspects may comprise a computer program product for performing the operations presented herein. For example, such a computer program product may comprise a computer-readable medium having instructions stored (and/or encoded) thereon, the instructions being executable by one or more processors to perform the operations described. For certain aspects, the computer program product may include packaging material):
obtaining reflective radar signals regarding a scene monitored (Garg, Abstract and para [0070]),
the reflective radar signals being received by multiple antennas of a radar sensor system (Garg, Abstract and para [0070]);
producing reflective-intensity data based on the reflective radar signals (Garg, para [0070]),
the reflective- intensity data containing multiple spatially invariant spectrums, which include (Garg, Abstract and para [0070])
1) a range reflective-intensity spectrum includes relative distances between reflection points indicated by the reflective-intensity data and the radar sensor system (Garg, paras [0070] and [0072]),
2) a speed ("Doppler") reflective-intensity spectrum includes speeds of the reflection points indicated by the reflective-intensity data relative to the radar sensor system (Garg, paras [0070] and [0072]),
and 3) an adjusted azimuth ("adjusted-azimuth") spectrum, which is based on azimuths of the reflection points indicated by the reflective-intensity data relative to the radar sensor system (Garg, paras [0070] and [0072]),
and wherein the producing includes determining a two-dimensional range- Doppler transform that incorporates the range reflective-intensity spectrum and Doppler reflective- intensity spectrum (Garg, paras [0070] and [0072]);
generating a reflective intensity volume (RIV) based on the reflective-intensity data (Garg, paras [0070] and [0072]);
applying a trained convolutional neural network (CNN) on the generated RIV (Garg, para [0042]);
and detecting objects in the scene based, at least in part, the applying of the trained CNN on the generated RIV (Garg, para [0042]).
Regarding claim 18, Garg discloses:
a non-transitory machine-readable storage medium of claim 17 (Garg, para [0145, col. 11 lines 6-16]),
wherein the determining the two-dimensional range-Doppler transform includes (Garg, para [0052]):
transforming the range reflective-intensity spectrum by the reflective radar signals (Garg, paras [0070] and [0072]),
wherein the range reflective-intensity spectrum includes range bins based on the reflective radar signals by multiple antennas of the radar sensor system (Garg, paras [0070] and [0072]);
and transforming the Doppler reflective-intensity spectrum by the reflective radar signals (Garg, paras [0070] and [0072]),
wherein the Doppler reflective-intensity spectrum includes Doppler bins based on the range bins and the reflective radar signals by multiple antennas of the radar sensor system (Garg, paras [0070] and [0072]).
Regarding claim 19, Garg disclose:
a non-transitory machine-readable storage medium of claim 18 (Garg, para [0145, col. 11 lines 6-16]),
wherein the producing reflective-intensity data includes determining the adjusted-azimuth spectrum by calculating sine of the azimuth ("sin(azimuth)") relative to a two-dimensional range-Doppler transform that incorporates the range reflective-intensity spectrum and Doppler reflective-intensity spectrum (Garg, paras [0052] and [0064]).
Regarding claim 20, Garg discloses:
a non-transitory machine-readable storage medium of claim 19, wherein (Garg, para [0145, col. 11 lines 6-16]):
the producing reflective-intensity data includes determining the adjusted-azimuth spectrum by calculating sine of the azimuth ("sin(azimuth)") relative to the range bins and Doppler bins of the two-dimensional range-Doppler transform (Garg, paras [0052] and [0064]);
and the generating includes combining results of the calculating for the range bins and Doppler to produce a three-dimensional, spatially invariant range-speed-adjusted-azimuth transform (Garg, para [0064]).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim 8 is rejected under Garg et al (US 20230366983 A1), hereinafter Garg in view of Raphaeli et al (US 20190250249 A1), hereinafter Raphaeli.
Regarding claim 8, Garg discloses:
a method of claim 7 (Garg, Abstract and para [0070]),
wherein each antenna of the multiple antennas having has a distance relative to other antennas of the multiple antennas and employing a radar signal having a defined wavelength (Garg, para [0070]),
and the calculating of the adjusted-azimuth spectrum includes performing (para [0011], n one aspect, the invention incorporates a Rotman lens into the radar system. The Rotman lens is operable to generate a plurality of time delayed, in phase signals necessary for beamforming, by exploiting the physical geometry of the lens cavity, reducing processing requirements for electrical switches or microelectronics-based switching for phase-shifters) and (para [0072]) Examiners notes that one of ordinary skill in the art understands that calculating the array response adjusted for the position of each antenna and the phase shift thereof:
wherein: "
PNG
media_image1.png
51
247
media_image1.png
Greyscale
The RIV is based on P(z), which is the reflection intensity at z=sin(azimuth) (Garg, paras [0011] and [0072]);
"n is cardinality of the multiple antennas (Garg, paras [0011] and [0072]);
"xn is a received radar signal at an n-th antenna (Garg, Fig. 5A);
"dn is the relative distance of an n-th antenna with respect to an antenna of the multiple antennas (Garg, Fig. 5A);
* is the defined wavelength of the radar signal (Garg, para [0070]);
;
*r is value of pi (Garg, para [0011]);
and * e is an exponential function (ie Euler’s number, mathematical constant ~ = 2.71828) (Garg, para [0011]).
Raphaeli discloses:
* j represents an imaginary number (Raphaeli , para [0038], The frequency shift hypotheses ω.sub.1 to ω.sub.L can be tested through using the Euler form e.sup.jω.sup.l.sup.t, where ω.sub.1 represents the l-th frequency shift hypothesis, t represents the time, and j is the imaginary number j. For each code n, each of the frequency shift hypotheses ω.sub.1 to ω.sub.L are mixed with each of the decoded offset signals D.sub.1,1 to D.sub.M,N to obtain a number of decoded hypothesis signals F.sub.1,1,1-F.sub.M,N,L. Thus, the number of decoded hypothesis signals is equal to N*L per receiving antenna. For example, step 262 depicts applying L frequency shift hypotheses to D.sub.1,1 to obtain L decoded hypothesis signals F.sub.1,1,1 to F.sub.1,1,L using frequency shift hypotheses ω.sub.1 to ω.sub.L. Similarly, step 264 depicts applying L frequency shift hypotheses to D.sub.M,N to obtain L decoded hypothesis signals F.sub.M,N,1 to F.sub.M,N,L using frequency shift hypotheses ω.sub.1 to ω.sub.L. The method then continues to step 270).
It would have been obvious to someone in the art prior to the effective filing date of the claimed invention to modify Garg with Raphaeli to incorporate the features of: * j represents an imaginary number. Both arts are considered analogous arts as they both disclose radar systems with beamforming methods for autonomous vehicles and semi-autonomous vehicles. The modification would render the predictable results of the imaginary number improved rejection of interference, improve angle of arrival estimation, and improved tracking.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Garg et al (US 20230366983 A1), hereinafter Garg in view of Fontijine et al (US 20210255304 A1), hereinafter Fontijine in further view of Foroozan et al (US 20210117659 A), hereinafter Foroozan.
Regarding claim 11, Garg discloses:
a device selected from a group consisting of an autonomous vehicle (Garg, para [0004], Convolutional neural networks are a type of feed-forward artificial neural network. Convolutional neural networks may include collections of neurons that each have a receptive field and that collectively tile an input space. Convolutional neural networks (CNNs), such as deep convolutional neural networks (DCNs), have numerous applications. In particular, these neural network architectures are used in various technologies, such as image recognition, pattern recognition, speech recognition, autonomous driving, and other classification tasks),
a semi-autonomous vehicle (Garg, para [0004]),
a video surveillance system (Garg, para [0057], The deep convolutional network 350 may also include one or more fully connected layers 362 (FC1 and FC2). The deep convolutional network 350 may further include a logistic regression (LR) layer 364. Between each layer 356, 358, 360, 362, 364 of the deep convolutional network 350 are weights (not shown) that are to be updated. The output of each of the layers (e.g., 356, 358, 360, 362, 364) may serve as an input of a succeeding one of the layers (e.g., 356, 358, 360, 362, 364) in the deep convolutional network 350 to learn hierarchical feature representations from input data 352 (e.g., images, audio, video, sensor data and/or other input data) supplied at the first of the convolution blocks 354A. The output of the deep convolutional network 350 is a classification score 366 for the input data 352. The classification score 366 may be a set of probabilities, where each probability is the probability of the input data including a feature from a set of features),
,
an object tracking system (Garg, Abstract),
the device being configured to perform the method of claim 1 (Garg, Abstract)
Fontijine discloses:
a video or image search or retrieval system (Fontijine, para [0048], In an aspect, the camera 212 may capture image frames (also referred to herein as camera frames) of the scene within the viewing area of the camera 212 (as illustrated in FIG. 1 as horizontal coverage zone 160) at some periodic rate. Likewise, the radar 214 may capture radar frames of the scene within the viewing area of the radar 214 (as illustrated in FIG. 1 as horizontal coverage zone 150) at some periodic rate. The periodic rates at which the camera 212 and the radar 214 capture their respective frames may be the same or different. Each camera and radar frame may be timestamped. Thus, where the periodic rates are different, the timestamps can be used to select simultaneously, or nearly simultaneously, captured camera and radar frames for further processing (e.g., fusion)) Examiner notes that fusion signal processing builds the reflective intensity volume, which is more useful for spatial invariance,
and a weather forecasting system (Fontijine, para [0005], The radar system provides reasonably accurate measurements of object distance and velocity in various weather conditions. However, radar systems typically have insufficient resolution to identify features of the detected objects. Camera sensors, however, typically do provide sufficient resolution to identify object features. The cues of object shapes and appearances extracted from the captured images may provide sufficient characteristics for classification of different objects. Given the complementary properties of the two sensors, data from the two sensors can be combined (referred to as “fusion”) in a single system for improved performance).
It would have been obvious to someone in the art prior to the effective filing date of the claimed invention to modify Garg with Fontijine to incorporate the features of: a video or image search or retrieval system, and a weather forecasting system. Both arts are considered analogous arts as they both disclose radar systems with convolutional neural networks and spatially invariant reflective data. The modification would render the predictable results of improved real-time surveillance, flight scheduling or agricultural planning.
The combination of Garg and Fontijine does not disclose: a medical imaging system, a video or image editing system.
Foroozan discloses:
a medical imaging system (Foroozan, para [0089, lines 1-16], In certain contexts, and as highlighted above, the features discussed herein can be applicable to medical systems, scientific instrumentation, wireless and wired communications, industrial process control, audio and video equipment, current sensing, instrumentation (which can be highly precise), and other digital-processing-based systems. Moreover, certain embodiments discussed above can be provisioned in digital signal processing technologies for medical imaging, patient monitoring, medical instrumentation, and home healthcare, as detailed extensively herein. This could include applications involving pulmonary monitors, accelerometers, heart rate monitors, pacemakers, etc. Other applications can involve automotive technologies for safety systems (e.g., stability control systems, driver assistance systems, braking systems, infotainment and interior applications of any kind)),
a video or image editing system (Foroozan, para [0065], In operation, first, when the multi-object tracking algorithm receives a list of detections, it starts by updating the target location of all the tracks. Second, the architecture sends the list of tracks found to the image clusters overlay algorithm to extract the portion of the image associated with the location. Third, the cropped images are sent to the CNN to check which kind of activity the target is performing. Fourth, the CNN output is sent back to the multi-object tracking algorithm to add the score and the label to the associated track. Also, there are other verifications that can be performed during this step. If the CNN returns background as a label with a score above a certain threshold, the track may be terminated).
It would have been obvious to someone in the art prior to the effective filing date of the claimed invention to modify the combination of Garg and Fontijine with Foroozan to incorporate the features of: a medical imaging system, a video or image editing system. The three arts disclose radar systems that utilizes Convolutional Neural Networks wherein reflective intensity data is obtained with associated reflective intensity volumes, which are essential to vehicles such as autonomous vehicles and detection of the surrounding areas of vehicles. The modification would render the predictable results of augment diagnostic imaging to improve patient outcomes, and the editing can improve the image resolution or restoration.
References Cited but not Relied Upon
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure as thus:
Harash et al (US 20160377704 A1) discloses human posture RF system, machine learning, data classification, spectrogram of motion over a range bin
Hoffman et al (US 20230314588 A1) discloses deep learning radar system capturing range and doppler directions
Kim (US-20210181306-A1) discloses radar data recognition with CNN, classifications, capturing speed, range, doppler
Kadambi (US-20230316571-A1) discloses sensor fusion between radar and optically polarized camera
Popov et al (US-12050285-B2) discloses deep neural networks for obstacle detection using radar for AV applications
Popov (US-11885907-B2) discloses deep neural networks for obstacle detection
Popov et al (US 20220206107 A1) discloses a MIMO antenna 32-element array, square virtual array, FFT processing to reduce the sidelobes and binary phase shifters
Ren (US-20240013521-A1) discloses antenna with CNN, spatially invariant data capturing speed, range for AV
Wang (US-20210311180-A1) discloses a radar antenna array for mobile user equipment including medical equipment
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KIMBERLY JENKINS whose telephone number is (571)272-0404. The examiner can normally be reached Monday - Friday 8a-5p EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Vladimir Magloire can be reached at 517.270.5144. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/KIMBERLY JENKINS/Examiner, Art Unit 3648
/VLADIMIR MAGLOIRE/Supervisory Patent Examiner, Art Unit 3648
Prosecution Insights