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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 1-4, 8-13, and 17-19 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Li et al. (ATTENTION RESIDUAL U-NET FOR BUILDING SEGMENTATION IN AERIAL IMAGES, hereinafter Li).
Regarding claim 1, Li discloses
A ground object segmentation method based on a residual module and an attention mechanism, comprising: obtaining a to-be-segmented remote sensing (RS) image, wherein the to-be-segmented RS image comprises multiple buildings and ground areas (Fig. 5, P. 3 Section 3.1 Experiment Preparation: “This paper uses Inria Aerial Image Labeling as core dataset, the dataset images cover five different urban settlements, ranging from densely populated areas to alpine towns with a total of 180 images.”); and
inputting the to-be-segmented RS image into a trained ground object segmentation model to obtain a ground object segmentation result, wherein the ground object segmentation result comprises a building segmentation result, and the ground object segmentation model is a network model obtained based on a U-Net neural network and with reference to the residual module and an attention module (Fig. 1-3 and 5, P. Section 2.1 Framework: “This paper proposes a novel ARU-net model based on U-net, adding two core parts: attention path and residual connection.”).
Regarding claims 8, 9, and 10, dependent upon claim 1, Li discloses everything regarding claim 1.
Li further discloses
Claim 8: A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program
Claim 9: A computer-readable storage medium, storing a computer program, wherein the computer program is executed by a processor
Claim 10: A computer program product, comprising a computer program, wherein the computer program is executed by a processor
to implement the steps of the ground object segmentation method based on a residual module and an attention mechanism according to claim 1 (P. 3 Section 3.1 Experiment Preparation: “In consideration of the experimental results fairly, each of network models is run on a single RTX 2080 GPU. Try best to make full use of memory, we set batch-size to 4, set the learning rate to10-5, and set momentum to 0.99”).
Regarding claim 2, 11, and 17, dependent upon claim 1, 8, and 9 respectively, Li discloses everything regarding claim 1, 8, and 9.
Li further discloses
obtaining a training dataset, wherein the training dataset comprises multiple training samples, and the training sample comprises a training RS image and a corresponding building segmentation label (P. 3 Section 3.1 Experiment Preparations: “This paper uses Inria Aerial Image Labeling as core dataset, the dataset images cover five different urban settlements, ranging from densely populated areas to alpine towns with a total of 180 images.”);
constructing the ground object segmentation model based on the U-Net neural network and with reference to the residual module and the attention module (Fig. 1-3, P. 3 Section 3.1 Experiment Preparations: “This paper uses intersection over union (IoU) and pixel accuracy (PA) as evaluation criteria, chooses 0.5 as the threshold to divide the probability map… And we use Adam optimizer and Binary_Crossentropy to train model.”); and
training the ground object segmentation model by using the training dataset to obtain a trained building segmentation model (P. 3 Section 3.1 Experiment Preparations: “This paper uses Inria Aerial Image Labeling as core dataset, the dataset images cover five different urban settlements, ranging from densely populated areas to alpine towns with a total of 180 images…This paper uses intersection over union (IoU) and pixel accuracy (PA) as evaluation criteria, chooses 0.5 as the threshold to divide the probability map… And we use Adam optimizer and Binary_Crossentropy to train model).
Regarding claim 3, 12, and 18, dependent upon claim 2, 11, and 17 respectively, Li discloses everything regarding claim 3, 12, and 18.
Li further discloses
for any training sample, inputting a training RS image of the training sample into the ground object segmentation model, and updating a model parameter of the ground object segmentation model by using a building segmentation label of the training sample as a target output (P. 3 Section 3.1 Experiment Preparations: “This paper uses Inria Aerial Image Labeling as core dataset, the dataset images cover five different urban settlements, ranging from densely populated areas to alpine towns with a total of 180 images…This paper uses intersection over union (IoU) and pixel accuracy (PA) as evaluation criteria, chooses 0.5 as the threshold to divide the probability map… And we use Adam optimizer and Binary_Crossentropy to train model).
Regarding claim 4, 13, and 19, dependent upon claim 1, 8, and 9 respectively, Li discloses everything regarding claim 1, 8, and 9.
Li further discloses
obtaining a test dataset, wherein the test dataset comprises multiple test samples, and the test sample comprises a test RS image and a corresponding building segmentation label (Fig. 5, P. 3 Section 3.1 Experiment Preparation: “This paper uses Inria Aerial Image Labeling as core dataset, the dataset images cover five different urban settlements, ranging from densely populated areas to alpine towns with a total of 180 images.”); and
testing the trained ground object segmentation model by using the test dataset, and determining building segmentation precision of the trained ground object segmentation model (Fig. 4-5).
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 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.
Claims 5, 14, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (ATTENTION RESIDUAL U-NET FOR BUILDING SEGMENTATION IN AERIAL IMAGES, hereinafter Li) in view of Liao et al. (CN 117495871 A, hereinafter Liao).
Regarding claim 5, 14, and 20, dependent upon claim 1, 8, and 9 respectively, Li discloses everything regarding claim 1, 8, and 9.
Li further discloses
the ground object segmentation model comprises an encoder and a decoder; the encoder and the decoder comprise the residual module (Fig. 3).
However Li does not explicitly disclose
the decoder comprises the attention module.
Liao teaches
the decoder comprises the attention module (Fig. 1, P. 2 Para. 4: “simultaneously introduces attention gates and convolution attention in a decoder to deeply excavate and extract different source features”, P. 4 Para. 12: “Input the attention gate structure of the first decoding block together to get the feature map”).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Li with having attention gates in decoder of U-Net of Liao to effectively increase the accuracy of segmentation.
Claims 6 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (ATTENTION RESIDUAL U-NET FOR BUILDING SEGMENTATION IN AERIAL IMAGES, hereinafter Li) in view of Liao et al. (CN 117495871 A, hereinafter Liao) and Punn et al. (RCA-IUnet: a residual cross-spatial attention-guided inception U-Net model for tumor segmentation in breast ultrasound imaging, hereinafter Punn).
Regarding claim 6 and 15, dependent upon claim 5 and 14 respectively, Li in view of Liao teaches everything regarding claim 5 and 14.
Li in view of Liao does not explicitly teach
the encoder comprises a first convolutional block, a second convolutional block, a third convolutional block, a fourth convolutional block, and a fifth convolutional block that are sequentially connected; the residual module comprises a first residual block, a second residual block, a third residual block, and a fourth residual block; the first residual block is connected between the first convolutional block and the second convolutional block; the second residual block is connected between the second convolutional block and the third convolutional block; the third residual block is connected between the third convolutional block and the fourth convolutional block; and the fourth residual block is connected between the fourth convolutional block and the fifth convolutional block.
Punn teaches
the encoder comprises a first convolutional block, a second convolutional block, a third convolutional block, a fourth convolutional block, and a fifth convolutional block that are sequentially connected; the residual module comprises a first residual block, a second residual block, a third residual block, and a fourth residual block; the first residual block is connected between the first convolutional block and the second convolutional block; the second residual block is connected between the second convolutional block and the third convolutional block; the third residual block is connected between the third convolutional block and the fourth convolutional block; and the fourth residual block is connected between the fourth convolutional block and the fifth convolutional block (Fig. 2 and 4, P. 4 Section 3.3 Inception convolution: “Consider
F
i
∈
R
w
×
h
×
d
an input feature map,, the overview of the inception convolution is illustrated in Fig. 4a. Following from the inception convolution layers, the residual inception convolution block is developed by applying double inception convolution layers with a short skip connection to merge the 1×1 extracted feature maps with input using
1
×
1
DSC as shown in Fig. 4b.”).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Li in view of Liao with having 5 convolutional modules with a residual module appending each for the encoder of a U-Net of Punn to effectively increase the accuracy of segmentation.
Allowable Subject Matter
Claims 7 and 16 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Relevant Prior Art Directed to State of Art
Wang et al. (Residual UNet with spatial and channel attention for automatic magnetic resonance image segmentation of rectal cancer, hereinafter Wang) is prior art not applied in the rejection(s) above. Wang discloses a residual UNet network model that combines spatial attention and channel attention. The model uses residual convolution for feature extraction, and uses squeeze-and-excitation module and attention gating module to focus on more useful features.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSHUA CHEN whose telephone number is (703)756-5394. The examiner can normally be reached M-Th: 9:30 am - 4:30pm ET F: 9:30 am - 2:30pm ET.
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, STEPHEN R KOZIOL can be reached at (408)918-7630. 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.
/J. C./ Examiner, Art Unit 2665
/Stephen R Koziol/ Supervisory Patent Examiner, Art Unit 2665
Prosecution Insights