CTNF 18/739,204 CTNF 101391 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. 1 st Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA 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 1, 4, 5, 9, and 10 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2024 0249435 A1 , (Griffith) in view of US Patent Publication 2023 0182743 A1 , (Lu et al. ) . Claim 1 Regarding claim 1 , Griffith teach an apparatus for determining positions of objects; the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and configured to: ("at least one processor; and at least one memory including computer program code, the at least one memory and the computer program code configured to," par. 16) obtain a first camera position related to a first image; ("receive a first image from a camera of an autonomous vehicle; acquire first camera pose constraints based on one or more static objects detected in the first image; receive a second image from the camera," par. 20) obtain a first vector, the first vector being based on the first camera position and a representation of an object in the first image; ("matching 2D points that are detected on the one or more dynamic objects in the first image to 2D points that are detected on the same objects in the second image," par. 8) obtain a first road-height model comprising three-dimensional positions of a road on which the object is positioned, ("Accurate estimates of vehicle positions and velocities are computed using the mathematical fusion of readings from RADAR, LiDAR, and the estimates from using camera pose and an HD map. The transmitted results contain the positions and the velocities for each of the detected vehicles," par. 51) wherein the first road-height model is related to the first camera position; ("estimating the at least one pose of the camera comprises aligning the stationary lane markings in one of the first and the second images with lane markings from a projected 3D map of a roadway," par. 12); and project the first vector from the first camera position to a point related to determine a first object position ("correcting the location of each projected 2D point comprises: receiving an estimate of a 3D position and a 3D velocity for each of the one or more dynamic objects; projecting each of the 3D position and velocity estimates into one of the first and second images to get a 2D vector; and adding the 2D vector to each projected 2D point on the same dynamic object," par. 9). Griffith do not explicitly teach all of obtain a second road-height model after obtaining the first road-height model; and a second road-height model. However, Lu et al. teach obtain a second road-height model after obtaining the first road-height model; ("obtaining a first ground model using the ground data; filling in a missing region of the first ground model to obtain a second ground model," par. 6) and a second road-height model ("second ground model," par. 6). Therefore, taking the teachings of Griffith and Lu et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify three-dimensional road estimation, object detection, and camera position estimation as taught by Griffith to use additional road-surface models as taught by Lu et al. The suggestion/motivation for doing so would have been that, “the processing device 15 fills in the missing region of the first ground model to obtain the second ground model … The missing region may be a blocked region or an undetected region. The digital inpainting may fill in any shape of the missing region” as noted by the Lu et al. disclosure in paragraph [0031], which also motivates combination because the combination would predictably have a higher efficiency as there is a reasonable expectation that digital inpainting techniques, such as those in Lu et al., could be applied to patch, reconstruct, or fill gaps in Griffith's ground model (the first ground model) to produce a complete or accurate revised model (the second ground model); and/or because doing so merely combines prior art elements according to known methods to yield predictable results. Claim 4 Regarding claim 4, Griffith and Lu et al. teach the apparatus of claim 1 as noted above. Griffith teach wherein the first vector is based on a projection from the first camera position through the representation of the object in the first image in an image plane to a point related to the first road-height model ("correcting the location of each projected 2D point comprises: receiving an estimate of a 3D position and a 3D velocity for each of the one or more dynamic objects; projecting each of the 3D position and velocity estimates into one of the first and second images to get a 2D vector; and adding the 2D vector to each projected 2D point on the same dynamic object," par. 9). Griffith and Lu et al. are combined as per claim 1. Claim 5 Regarding claim 5, Griffith and Lu et al. teach the apparatus of claim 1 as noted above. Griffith teach wherein the at least one processor is configured to: obtain a plurality of camera positions, wherein each camera position of the plurality of camera positions is related to a respective image of a plurality of images; ("In some embodiments, the computer 50 can perform the projection using the geometric model described in EQN. 4, which can be constructed from the camera poses corresponding to the two consecutive images," par. 56) obtain a plurality of vectors, wherein each vector of the plurality of vectors is based on a respective camera position of the plurality of camera positions and a representation of the object in a respective image of the plurality of images; ("the method further comprises: detecting locations of the one or more dynamic objects in the first and the second images; matching 2D points that are detected on the one or more dynamic objects in the first image to 2D points that are detected on the same objects in the second image; estimating a homography from orientations of a first camera pose associated with the first image and a second camera pose associated with the second image," par. 8) and project each vector of the plurality of vectors from a respective camera position to a respective point to determine a respective updated object position of a plurality of updated object positions ("correcting the location of each projected 2D point comprises: receiving an estimate of a 3D position and a 3D velocity for each of the one or more dynamic objects; projecting each of the 3D position and velocity estimates into one of the first and second images to get a 2D vector; and adding the 2D vector to each projected 2D point on the same dynamic object," par. 9). Griffith do not explicitly teach all of the second road-height model. However, Lu et al. teach the second road-height model ("second ground model," par. 6). Griffith and Lu et al. are combined as per claim 1. Claim 9 Regarding claim 9, Griffith and Lu et al. teach the apparatus of claim 1 as noted above. Griffith teach wherein the object comprises at least one of: a lane marking on the road; and a symbol on the road; or traffic information on the road ("In some embodiments, the one or more static objects comprise stationary lane markings," par. 11). Griffith and Lu et al. are combined as per claim 1. Claim 10 Regarding claim 10, Griffith and Lu et al. teach the apparatus of claim 1 as noted above. Griffith teach wherein the apparatus comprises a computing device of a vehicle ("These images can be analyzed by a computer on-board the autonomous vehicle," par. 30). Griffith and Lu et al. are combined as per claim 1. 2 nd Claim Rejections - 35 USC § 103 Claims 2, 3, and 6 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2024 0249435 A1 , (Griffith) and US Patent Publication 2023 0182743 A1 , (Lu et al. ) in view of US Patent Publication 2020 0049479 A1 , (Psiuk et al. ). Claim 2 Regarding claim 2, Griffith and Lu et al. teach the apparatus of claim 1 as noted above. [AltContent: textbox (Figure 1B shows points detected from the previous image overlaid onto the current image.)] PNG media_image1.png 404 680 media_image1.png Greyscale Griffith teach wherein the at least one processor is configured to: obtain a second camera position related to a second image; ("acquire second camera pose constraints based on one or more static objects detected in the second image," par. 16) project a second vector from the second camera position through a representation of the object in the second image to a point to determine a second object position; ("In the embodiment of FIG. 1B, the first points 602 are detected in a current image and the second points 604 are detected in the previous image. The computer 50 can project the second points 604 from the previous image into the current image to obtain the visualization of FIG. 1B," par. 56). Lu et al. teach the second road-height model ("second ground model," par. 6). Griffith and Lu et al. do not explicitly teach all of determine a third object position based on the second object position and the first object position. However, Psiuk et al. teach determine a third object position based on the second object position and the first object position ("the position of the movable object may in some embodiments further comprise determining a weighted average value of the positions of the movable object allocated to the number of the reference values as the position of the movable object," par. 46). Therefore, taking the teachings of Griffith , Lu et al. , and Psiuk et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify three-dimensional road estimation, object detection, and camera position estimation as taught by Griffith to use additional road surface-models as taught by Lu et al. and object position estimation as taught by Psiuk et al. The suggestion/motivation for doing so would have been that, “positions may be estimated which are not within the grid of the table. Thus, an interpolation effect may be achieved which increases the accuracy of the position estimate far beyond the grid of the table. Thus, the position grid in the simulation of the table may be selected coarser than e.g. in the above represented embodiments. Thus, an exact localization may be acquired without simulating a very fine grid at positions with many table entries. This may shorten a simulation period, reduce a memory occupancy of the table and shorten a search in the table in the actual localization. A real-time localization may therefore be enabled. A weighted k-nearest localization method may thus simultaneously enable an increase of the localization accuracy and a size reduction of the table” as noted by the Psiuk et al. disclosure in paragraph [0054], which also motivates combination because the combination would predictably have a higher accuracy as there is a reasonable expectation that the system would be provided better localization accuracy without the computational burden of a high-resolution, dense memory grid; and/or because doing so merely combines prior art elements according to known methods to yield predictable results. Claim 3 Regarding claim 3, Griffith and Lu et al. teach the apparatus of claim 2 as noted above. Griffith and Lu et al. do not explicitly teach all of wherein the third object position is based on a weighted average of the second object position and the first object position. However, Psiuk et al. teach wherein the third object position is based on a weighted average of the second object position and the first object position ("the position of the movable object may in some embodiments further comprise determining a weighted average value of the positions of the movable object allocated to the number of the reference values as the position of the movable object," par. 46). Griffith , Lu et al. , and Psiuk et al. are combined as per claim 2. Claim 6 Regarding claim 6, Griffith and Lu et al. teach the apparatus of claim 5 as noted above. Griffith teach wherein the at least one processor is configured to: obtain a second camera position related to a second image; ("acquire second camera pose constraints based on one or more static objects detected in the second image," par. 16) project a second vector from the second camera position through a representation of the object in the second image in an image plane to a point related to the second road-height model to determine a second object position; ("In the embodiment of FIG. 1B, the first points 602 are detected in a current image and the second points 604 are detected in the previous image. The computer 50 can project the second points 604 from the previous image into the current image to obtain the visualization of FIG. 1B," par. 56). Griffith and Lu et al. do not explicitly teach all of determine a third object position based on the second object position and the plurality of updated object positions. However, Psiuk et al. teach determine a third object position based on the second object position and the plurality of updated object positions ("the position of the movable object may in some embodiments further comprise determining a weighted average value of the positions of the movable object allocated to the number of the reference values as the position of the movable object," par. 46). Griffith , Lu et al. , and Psiuk et al. are combined as per claim 2. 3 rd Claim Rejections - 35 USC § 103 Claim 7 is rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2024 0249435 A1 , (Griffith) and US Patent Publication 2023 0182743 A1 , (Lu et al. ) in view of US Patent Publication 2022 0067396 A1, (Okubo). Claim 7 Regarding claim 7, Griffith and Lu et al. teach the apparatus of claim 1 as noted above. Griffith teach wherein the first vector is determined based on a filtered object position ("the computer 50 can be configured to filter vehicles (i.e., discard vehicles from further consideration) according to their distance to the autonomous vehicle," par. 52) and a filtered camera position; and the first camera position comprises the filtered camera position ("Consumers of the camera pose running on the computer 50 (e.g., modules for tracking, depth estimation, and speed estimation of objects) can filter camera pose estimates with low confidence," par. 84). Griffith do not explicitly teach all of the first vector comprises a filtered vector. However, Okubo teach the first vector comprises a filtered vector ("the road surface determination unit 172 may use a Hough transformation relating to a straight line, to keep solely the representative distances that form the same straight line or form not the same straight line but a parallel straight line within a predetermined relative distance. The road surface determination unit 172 may exclude the other representative distances surrounded by broken lines in FIG. 7B as noise," par. 46). Therefore, taking the teachings of Griffith, Lu et al., and Okubo as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify three-dimensional road estimation, object detection, and camera position estimation as taught by Griffith and additional road surface-models as taught by Lu et al. to use filtered vector points as taught by Okubo The suggestion/motivation for doing so would have been that, “The road surface determination unit 172 may exclude the other representative distances surrounded by broken lines in FIG. 8B as noise. The road surface determination unit 172 may calculate an approximate straight line of such a point cloud by, for example, the least squares method, targeting solely at the remaining representative distances. In this way, the road surface model 236 having a different gradient may be newly generated” as noted by the Okubo disclosure in paragraph [0050], which also motivates combination because the combination would predictably have a higher accuracy as there is a reasonable expectation that road surface modeling accuracy would be improved by eliminating noisy, irrelevant, or outlier data points from the calculation, resulting in a more precise and stable model; and/or because doing so merely combines prior art elements according to known methods to yield predictable results. 4 th Claim Rejections - 35 USC § 103 Claim 8 is rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2024 0249435 A1 , (Griffith) and US Patent Publication 2023 0182743 A1 , (Lu et al. ) in view of US Patent Publication 2022 0067396 A1, (Okubo) and US Patent Publication 2021 0209785 A1 , (Unnikrishnan et al. ). Claim 8 Regarding claim 8, Griffith, Lu et al., and Okubo teach the apparatus of claim 7 as noted above. Griffith, Lu et al., and Okubo do not explicitly teach all of wherein the filtered object position is determined using a Kalman filter. However, Unnikrishnan et al. teach wherein the filtered object position is determined using a Kalman filter ("the estimation model is a Kalman filter," par. 21). Therefore, taking the teachings of Griffith, Lu et al., Okubo, and Unnikrishnan et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify three-dimensional road estimation, object detection, and camera position estimation as taught by Griffith, additional road surface-models as taught by Lu et al., and filtered vector points as taught by Okubo to use the Kalman filter and object position operating parameter as taught by Unnikrishnan et al. The suggestion/motivation for doing so would have been that, “ the tracking vehicle 102 can determine the position and size of the target vehicle 104 to determine when to slow down, speed up, change lanes, and/or perform some other function” as noted by the Unnikrishnan et al. disclosure in paragraph [0055], which also motivates combination because the combination would predictably have additional utility as there is a reasonable expectation that the tracking vehicle can make proactive, real-time safety and operational decisions, such as automatic braking, lane-keeping, or acceleration, based on accurate, filtered, three-dimensional spatial data regarding surrounding objects; and/or because doing so merely combines prior art elements according to known methods to yield predictable results. 5 th Claim Rejections - 35 USC § 103 Claims 11 and 12 is rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2024 0249435 A1 , (Griffith) and US Patent Publication 2023 0182743 A1 , (Lu et al. ) in view of US Patent Publication 2021 0209785 A1 , (Unnikrishnan et al. ). Claim 11 Regarding claim 11, Griffith and Lu et al. teach the apparatus of claim 10 as noted above. Griffith and Lu et al. do not explicitly teach all of wherein the at least one processor is configured to adjust an operating parameter of the vehicle based on first object position. However, Unnikrishnan et al. teach wherein the at least one processor is configured to adjust an operating parameter of the vehicle based on first object position ("the tracking vehicle 102 can determine the position and size of the target vehicle 104 to determine when to slow down, speed up, change lanes, and/or perform some other function," par. 55). Griffith, Lu et al., and Unnikrishnan et al. are combined as per claim 8. Claim 12 Regarding claim 12, Griffith, Lu et al., and Unnikrishnan et al. teach the apparatus of claim 11 as noted above. Griffith and Lu et al. do not explicitly teach all of wherein the operating parameter is associated with at least one of a path for the vehicle to travel, an automatic braking parameter for operating one or more brakes of the vehicle, a lane change parameter for causing the vehicle to navigate from a first lane to a second lane, or displaying information based on the first object position using a user interface of the vehicle. However, Unnikrishnan et al. teach wherein the operating parameter is associated with at least one of a path for the vehicle to travel, an automatic braking parameter for operating one or more brakes of the vehicle, a lane change parameter for causing the vehicle to navigate from a first lane to a second lane, or displaying information based on the first object position using a user interface of the vehicle ("the tracking vehicle 102 can determine the position and size of the target vehicle 104 to determine when to slow down, speed up, change lanes, and/or perform some other function," par. 55). Griffith, Lu et al., and Unnikrishnan et al. are combined as per claim 8. 6 th Claim Rejections - 35 USC § 103 Claims 13, 18, and 19 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2024 0249435 A1 , (Griffith) in view of US Patent Publication 2022 0067396 A1, (Okubo). Claim 13 Regarding claim 13 , Griffith teach an apparatus for determining positions of objects; the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and configured to: ("at least one processor; and at least one memory including computer program code, the at least one memory and the computer program code configured to," par. 16) obtain a filtered camera position; ("Consumers of the camera pose running on the computer 50 (e.g., modules for tracking, depth estimation, and speed estimation of objects) can filter camera pose estimates with low confidence," par. 84) obtain a vector, ("matching 2D points that are detected on the one or more dynamic objects in the first image to 2D points that are detected on the same objects in the second image," par. 8) the vector being based on the filtered camera position, ("estimating the at least one pose of the camera comprises aligning the stationary lane markings in one of the first and the second images with lane markings from a projected 3D map of a roadway," par. 12) and a filtered object position, where in the filtered object position is based on a first road-height model ("Accurate estimates of vehicle positions and velocities are computed using the mathematical fusion of readings from RADAR, LiDAR, and the estimates from using camera pose and an HD map. The transmitted results contain the positions and the velocities for each of the detected vehicles," par. 51); and project the filtered vector from the filtered camera position to a point related to the road-height model to determine an updated filtered object position ("correcting the location of each projected 2D point comprises: receiving an estimate of a 3D position and a 3D velocity for each of the one or more dynamic objects; projecting each of the 3D position and velocity estimates into one of the first and second images to get a 2D vector; and adding the 2D vector to each projected 2D point on the same dynamic object," par. 9). Griffith do not explicitly teach all of a filtered vector, obtain a second road-height model, wherein the second road-height model comprises three-dimensional positions of a road on which an object is positioned; and a second road-height model. However, Okubo teach a filtered vector, ("the road surface determination unit 172 may use a Hough transformation relating to a straight line, to keep solely the representative distances that form the same straight line or form not the same straight line but a parallel straight line within a predetermined relative distance. The road surface determination unit 172 may exclude the other representative distances surrounded by broken lines in FIG. 7B as noise," par. 46) obtain a second road-height model, wherein the second road-height model comprises three-dimensional positions of a road on which an object is positioned; ("The three-dimensional object determination unit 174 may group the blocks to put any two or more of the blocks that are positioned vertically upward of the first road surface model and the second surface model in a group and thereby determine three-dimensional objects," par. 29) and a second road-height model ("second road surface model," par. 29). Therefore, taking the teachings of Griffith and Okubo as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify three-dimensional road estimation, object detection, and camera position estimation as taught by Griffith to use additional road-surface models as taught by Okubo The suggestion/motivation for doing so would have been that, “The second road surface model represents a farther portion of the road surface region from an own vehicle than the first road surface model and differs in a gradient from the first road surface model” as noted by the Okubo disclosure in paragraph [0005], which also motivates combination because the combination would predictably have a higher efficiency as there is a reasonable expectation that using multiple road-surface models with different gradients allows for a more accurate modeling of road topography over varying distances, thereby reducing estimation errors in three-dimensional road and camera position detection; and/or because doing so merely combines prior art elements according to known methods to yield predictable results. Claim 18 Regarding claim 18, Griffith and Okubo teach the apparatus of claim 13 as noted above. Griffith teach the apparatus of claim 13, wherein the object comprises at least one of: a lane marking on the road; and a symbol on the road; or traffic information on the road ("In some embodiments, the one or more static objects comprise stationary lane markings," par. 11). Griffith and Okubo are combined as per claim 7 and 13. Claim 19 Regarding claim 19, Griffith and Okubo teach the apparatus of claim 13 as noted above. Griffith teach wherein the apparatus comprises a computing device of a vehicle ("These images can be analyzed by a computer on-board the autonomous vehicle," par. 30). Griffith and Okubo are combined as per claim 7 and 13. 7 th Claim Rejections - 35 USC § 103 Claims 14 and 20 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2024 0249435 A1 , (Griffith) and US Patent Publication 2022 0067396 A1 , (Okubo) in view of US Patent Publication 2021 0209785 A1 , (Unnikrishnan et al. ). Claim 14 Regarding claim 14, Griffith and Okubo teach the apparatus of claim 13 as noted above. Griffith and Okubo do not explicitly teach all of wherein the filtered object position is determined using a Kalman filter. However, Unnikrishnan et al. teach wherein the filtered object position is determined using a Kalman filter ("the estimation model is a Kalman filter," par. 21). Griffith , Okubo, and Unnikrishnan et al. are combined as per claim 8. Claim 20 Regarding claim 20, Griffith , Okubo, and Unnikrishnan et al. teach the apparatus of claim 19 as noted above. Griffith teach updated filtered object position ("the computer 50 can be configured to filter vehicles (i.e., discard vehicles from further consideration) according to their distance to the autonomous vehicle," par. 52). Griffith and Okubo do not explicitly teach all of wherein the at least one processor is configured to adjust an operating parameter of the vehicle. However, Unnikrishnan et al. teach wherein the at least one processor is configured to adjust an operating parameter of the vehicle ("the tracking vehicle 102 can determine the position and size of the target vehicle 104 to determine when to slow down, speed up, change lanes, and/or perform some other function," par. 55). Griffith , Okubo, and Unnikrishnan et al. are combined as per claim 8. 8 th Claim Rejections - 35 USC § 103 Claims 15, 16, and 17 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2024 0249435 A1 , (Griffith) and US Patent Publication 2022 0067396 A1 , (Okubo) in view of US Patent Publication 2020 0049479 A1 , (Psiuk et al. ). Claim 15 Regarding claim 5, Griffith and Okubo teach the apparatus of claim 13 as noted above. Griffith teach obtain a second camera position related to a second image ("acquire second camera pose constraints based on one or more static objects detected in the second image," par. 16); project a second vector from the second camera position through a representation of an object in the second image in an image plane to a point to determine a second object position ("In the embodiment of FIG. 1B, the first points 602 are detected in a current image and the second points 604 are detected in the previous image. The computer 50 can project the second points 604 from the previous image into the current image to obtain the visualization of FIG. 1B," par. 56). Okubo teach the second road-height model ("second road surface model," par. 29). Griffith and Okubo do not explicitly teach all of determine a third object position based on the second object position and the updated filtered object position. However, Psiuk et al. teach determine a third object position based on the second object position and the updated filtered object position ("the position of the movable object may in some embodiments further comprise determining a weighted average value of the positions of the movable object allocated to the number of the reference values as the position of the movable object," par. 46). Griffith , Okubo, and Psiuk et al. are combined as per claim 2. Claim 16 Regarding claim 16, Griffith , Okubo, and Psiuk et al. teach the apparatus of claim 15 as noted above. Griffith teach the filtered camera position comprises a first filtered camera position ("Consumers of the camera pose running on the computer 50 (e.g., modules for tracking, depth estimation, and speed estimation of objects) can filter camera pose estimates with low confidence," par. 84); the updated filtered object position comprises a first updated filtered object position ("the computer 50 can be configured to filter vehicles (i.e., discard vehicles from further consideration) according to their distance to the autonomous vehicle," par. 52); and the at least one processor is configured to: ("at least one processor; and at least one memory including computer program code, the at least one memory and the computer program code configured to," par. 16) store the second camera position as a second filtered camera position; ("Consumers of the camera pose running on the computer 50 (e.g., modules for tracking, depth estimation, and speed estimation of objects) can filter camera pose estimates with low confidence," par. 84) project the second filtered vector from the second filtered camera position to the third road-height model to determine a second updated filtered object position ("correcting the location of each projected 2D point comprises: receiving an estimate of a 3D position and a 3D velocity for each of the one or more dynamic objects; projecting each of the 3D position and velocity estimates into one of the first and second images to get a 2D vector; and adding the 2D vector to each projected 2D point on the same dynamic object," par. 9). Griffith do not explicitly teach all of the filtered vector comprises a first filtered vector; store the second vector as a second filtered vector; and obtain a third road-height model. However, Okubo teach the filtered vector comprises a first filtered vector; ("the road surface determination unit 172 may use a Hough transformation relating to a straight line, to keep solely the representative distances that form the same straight line or form not the same straight line but a parallel straight line within a predetermined relative distance. The road surface determination unit 172 may exclude the other representative distances surrounded by broken lines in FIG. 7B as noise," par. 46) store the second vector as a second filtered vector; ("The road surface determination unit 172 may keep solely the representative distances that form the same straight line or form not the same straight line but a parallel straight line within a predetermined relative distance," par. 48) and obtain a third road-height model ("second road surface model," par. 29). Griffith , Okubo, and Psiuk et al. are combined as per claim 2. Claim 17 Regarding claim 17, Griffith , Okubo, and Psiuk et al. teach the apparatus of claim 16 as noted above. Griffith teach obtain a third camera position related to a third image; ("acquire second camera pose constraints based on one or more static objects detected in the second image," par. 16) project a third vector from the third camera position through a representation of the object in the third image in an image plane to determine a fourth object position ("In the embodiment of FIG. 1B, the first points 602 are detected in a current image and the second points 604 are detected in the previous image. The computer 50 can project the second points 604 from the previous image into the current image to obtain the visualization of FIG. 1B," par. 56). Okubo teach the third road-height model ("second road surface model," par. 29). Griffith and Okubo do not explicitly teach all of determine a third updated object position based on the fourth object position and the second updated filtered object position. However, Psiuk et al. teach determine a third updated object position based on the fourth object position and the second updated filtered object position ("the position of the movable object may in some embodiments further comprise determining a weighted average value of the positions of the movable object allocated to the number of the reference values as the position of the movable object," par. 46). Griffith , Okubo, and Psiuk et al. are combined as per claim 2. Reference Cited 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. US Patent Publication 2021 0049780 A1 to Westmacot et al. discloses using a time sequence of two-dimensional images to reconstruct a path travelled by a vehicle and expected road structure by performing geometric projection . Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to KARSTEN F LANTZ whose telephone number is (571) 272-4564. The examiner can normally be reached Monday-Friday 8:00-4:00. 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, Ms. Jennifer Mehmood can be reached on 571-272-2976. 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. /Karsten F. Lantz/Examiner, Art Unit 2664 Date: 3/17/2026 /JENNIFER MEHMOOD/Supervisory Patent Examiner, Art Unit 2664 Application/Control Number: 18/739,204 Page 2 Art Unit: 2664 Application/Control Number: 18/739,204 Page 3 Art Unit: 2664 Application/Control Number: 18/739,204 Page 4 Art Unit: 2664 Application/Control Number: 18/739,204 Page 5 Art Unit: 2664 Application/Control Number: 18/739,204 Page 6 Art Unit: 2664 Application/Control Number: 18/739,204 Page 7 Art Unit: 2664 Application/Control Number: 18/739,204 Page 8 Art Unit: 2664 Application/Control Number: 18/739,204 Page 9 Art Unit: 2664 Application/Control Number: 18/739,204 Page 10 Art Unit: 2664 Application/Control Number: 18/739,204 Page 11 Art Unit: 2664 Application/Control Number: 18/739,204 Page 12 Art Unit: 2664 Application/Control Number: 18/739,204 Page 13 Art Unit: 2664 Application/Control Number: 18/739,204 Page 14 Art Unit: 2664 Application/Control Number: 18/739,204 Page 15 Art Unit: 2664 Application/Control Number: 18/739,204 Page 16 Art Unit: 2664 Application/Control Number: 18/739,204 Page 17 Art Unit: 2664 Application/Control Number: 18/739,204 Page 18 Art Unit: 2664 Application/Control Number: 18/739,204 Page 19 Art Unit: 2664 Application/Control Number: 18/739,204 Page 20 Art Unit: 2664 Application/Control Number: 18/739,204 Page 21 Art Unit: 2664 Application/Control Number: 18/739,204 Page 22 Art Unit: 2664 Application/Control Number: 18/739,204 Page 23 Art Unit: 2664 Application/Control Number: 18/739,204 Page 24 Art Unit: 2664
Prosecution Insights