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
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed on 4 January, 2023.
Response to Amendment
The amendment filed 11 August, 2025 has been entered.
The amendment of the specification has been acknowledged.
The amendment of claims 1, and 5 - 10 has been acknowledged.
Response to Arguments
Applicant’s arguments, see page 7, section “Specification Objection”, filed 11 August, 2025 with respect to the objection of the abstract have been fully considered and are persuasive. The objection of the abstract has been withdrawn.
Applicant’s arguments, see page 7, section “Claim Objections”, filed 11 August, 2025 with respect to the objection of claims 6 and 9 have been fully considered and are persuasive. The objection of claims 6 and 9 have been withdrawn.
Applicant’s arguments, see page 7, section “Claim Rejections – 35 U.S.C. 101”, filed 11 August, 2025 with respect to the rejections of claims 1 - 12 have been fully considered and are persuasive. The rejections of claims 1 - 12 under 35 U.S.C. 101 have been withdrawn.
Applicant’s arguments, see page 12, section “Claim Rejections – 35 U.S.C. 102 & 103”, filed 11 August, 2025 with respect to the rejection of claims 1 – 3, 5, and 8 have been fully considered and are persuasive. The rejections of claims 1 – 3, 5, and 8 under 35 U.S.C. 102 have been withdrawn. However, upon further examination, a new rejection of these claims under 35 U.S.C. 103 has been made.
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.
Claims 1 – 3, and 5 – 9 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Kuramoto et al (A. Kuramoto, M. A. Aldibaja, R. Yanase, J. Kameyama, K. Yoneda and N. Suganuma, "Mono-Camera based 3D Object Tracking Strategy for Autonomous Vehicles," 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China, 2018, pp. 459-464, doi: 10.1109/IVS.2018.8500482, hereinafter “Kuramoto”) in view of Nakayama et al (U.S Patent No. 5790403, hereinafter “Nakayama”).
Regarding claim 1, Kuramoto teaches a method of an autonomous vehicle for estimating a distance to an object captured by a mono camera of the autonomous vehicle (Abstract: This paper proposes an approach to calculate 3D positions of far detected vehicles. Mainly, the distance from the vehicles during autonomous driving must be estimated precisely to strategize a safe path planning.), the method comprising:
a camera height input step of receiving a height of the mono camera installed in parallel to a ground the autonomous vehicle is travelling (Figure 2; Page 459, Column 2, ¶ 5: In this paper, we propose a framework for detecting far objects and estimating the corresponding distance to the vehicle using mono-camera and GNSS/IMU system.; Page 460, Column 2, ¶ 1: In order to estimate the position in the real world, four coordinate systems are used as shown in Fig. 2, i.e., camera coordinates system (CCS), vehicle coordinates system (VCS) and world coordinate system (WCS).),
a reference value setting step of setting at least one reference value among a vertical viewing angle, an azimuth angle, and a resolution of the mono camera (Figure 2, Equation 1; Page 460, Column 2, ¶ 1: Mathematically, the transformation between these systems can be explained by rotation and translation matrices [Rth Tth] with respect to the origin and the axes directions… The offsets of the rotation angles between these two systems are estimated using (1) based on the measurements of the GNSS/IMU system.; Page 460, Column 2, ¶ 2: α[n] is an angle (roll, pitch or yaw) measured on time tn, and Δα[n] is the estimated offset, respectively. Therefore, α[n] - Δα[n] is an angle of the estimated road plane.);
a pixel coordinate estimation step of estimating a three-dimensional coordinate value for at least some of pixels in a two-dimensional image of the object with respect to ground of the two-dimensional image of the object captured by the mono camera based on the height of the mono camera and the at least one reference value (Figure 2 and 3; Page 460, Column 2, Section C: Figure 3 shows the flowchart of estimating the 3D object position in WCS from CCS… Accordingly, a 3D position of an object in CCS = cp = (cp-x, cp-y,, cp-z), can be described as follows:
PNG
media_image1.png
67
326
media_image1.png
Greyscale
As the object is assumed the be in the road plane, (3) can be rewritten to (4).
PNG
media_image2.png
79
308
media_image2.png
Greyscale
); and
an object distance estimation step of estimating the distance to the object included in the two-dimensional image (Page 461, Column 1, Section D: As the distance estimation of far objects is a main objective, the image region closer to the horizon curve has a larger difference between adjacent pixels as shown in Fig. 4… Object in WCS is described by a state vector
X
^
=
[
p
x
w
,
p
y
w
,
p
˙
x
w
,
p
˙
x
w
,
p
¨
x
w
p
¨
x
w
]
T
which contains the values of position, velocity and acceleration values in x and y directions, respectively. A measurement vector of the object position in the image domain is expressed by
Z
^
=
[
u
,
v
]
T
.).
Kuramoto does not explicitly teach wherein the height of the mono camera is measured by a distance measurement sensor installed on the autonomous vehicle.
However, Nakayama does teach wherein the height of the mono camera is measured by a distance measurement sensor installed on the autonomous vehicle (Column 6, Line 31 – 41: This is for use in correcting the position and elevation of the CCD camera 10, which change owing to change in the attitude (pitch angle) of the vehicle during acceleration or deceleration. Specifically. this is achieved by mounting height sensors at the four corners of the vehicle (these sensors are omitted from FIGS. 1 and 2), determining the positional relationship between the vehicle and the road surface, and using the information obtained to correct the camera elevation, thereby preventing errors in mapping calculations between coordinates in the image and coordinates in the actual plane coordinates.).
Kuramoto and Nakayama are considered to be analogous art as both pertain to image processing for vehicles. Therefore, it would have been obvious to one of ordinary skill in the art to combine the mono-camera based 3D object tracking strategy for autonomous vehicles (as taught by Kuramoto) and the lane image processing system for vehicle (as taught by Nakayama) before the effective filing date of the claimed invention. The motivation for this combination of references would be the system of Nakayama utilizes height sensors to correct the camera elevation, thereby preventing errors in mapping calculations in the image and coordinates in the actual plane coordinates (See Column 6).
This motivation for the combination of Kuramoto and Nakayama is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Regarding claim 2, the Kuramoto and Nakayama combination teaches the method according to claim 1.
Additionally, Kuramoto teaches wherein the pixel coordinate estimation step includes a modeling process of estimating the three-dimensional coordinate value by generating a three-dimensional point using a pinhole camera model (Equation 2, 3, 4, 5; Page 460, Column 2, Section C: Based on the pinhole camera model, the normalized image coordinates (x”, y”) are calculated from u, v) as follows….).
Regarding claim 3, the Kuramoto and Nakayama combination teaches the method according to claim 2.
Additionally, Kuramoto teaches wherein the pixel coordinate estimation step further includes, after the modeling process, a lens distortion correction process of correcting distortion generated by a lens of the mono camera (Figure 3; Equation 9, 10, and 11; Page 461, Column 2, ¶ 1: By considering the camera distortion parameters (k1, k2, c1, c2) as in (9) and (10), ht is represented in (11) with respect to the undistorted position (X”, y”)).
Regarding claim 5, Kuramoto teaches a method of an autonomous vehicle for a distance to an object captured by a mono camera of the autonomous vehicle (Abstract: This paper proposes an approach to calculate 3D positions of far detected vehicles. Mainly, the distance from the vehicles during autonomous driving must be estimated precisely to strategize a safe path planning.), the method comprising:
a two-dimensional image acquisition step of acquiring a two-dimensional image of the object captured by the mono camera (Figure 2; Page 459, Column 2, ¶ 5: In this paper, we propose a framework for detecting far objects and estimating the corresponding distance to the vehicle using mono-camera and GNSS/IMU system.), wherein the mono camera is installed in parallel to a ground the autonomous vehicle is travelling (Page 460, Column 1, Section II: The image is captured by a front camera and inputted to a trained DCNN.)
a pixel coordinate estimation step of estimating a three-dimensional coordinate value for at least some of pixels of a two-dimensional image of the object with respect to a ground of the two-dimensional image of the object captured by the mono camera based on at least the height of the mono camera (Figure 2 and 3; Page 460, Column 2, Section C: Figure 3 shows the flowchart of estimating the 3D object position in WCS from CCS… Accordingly, a 3D position of an object in CCS = cp = (cp-x, cp-y,, cp-z), can be described as follows:
PNG
media_image1.png
67
326
media_image1.png
Greyscale
As the object is assumed the be in the road plane, (3) can be rewritten to (4).
PNG
media_image2.png
79
308
media_image2.png
Greyscale
);
a coordinate system matching step of matching each pixel of the two-dimensional image and a three-dimensional coordinate system (Figure 2 and 3; Page 460, Column 2, Section C: Figure 3 shows the flowchart of estimating the 3D object position in WCS from CCS… Accordingly, a 3D position of an object in CCS = cp = (cp-x, cp-y,, cp-z), can be described as follows:
PNG
media_image1.png
67
326
media_image1.png
Greyscale
As the object is assumed the be in the road plane, (3) can be rewritten to (4).
PNG
media_image2.png
79
308
media_image2.png
Greyscale
); and
an object distance estimation step of estimating the distance to the object included in the two-dimensional image (Page 461, Column 1, Section D: As the distance estimation of far objects is a main objective, the image region closer to the horizon curve has a larger difference between adjacent pixels as shown in Fig. 4… Object in WCS is described by a state vector
X
^
=
[
p
x
w
,
p
y
w
,
p
˙
x
w
,
p
˙
x
w
,
p
¨
x
w
p
¨
x
w
]
T
which contains the values of position, velocity and acceleration values in x and y directions, respectively. A measurement vector of the object position in the image domain is expressed by
Z
^
=
[
u
,
v
]
T
.)
Additionally, Nakayama teaches wherein the mono camera is installed in parallel to a ground the autonomous vehicle is travelling (Column 5, Line 5 – 8: The CCD (charged-coupled device) camera (image sensor) is mounted above the driver’s seat in the vicinity of the rearview mirror to capture the monocular view of the road ahead.) and a height of the mono camera is measured by a distance measurement sensor installed on the autonomous vehicle (Column 6, Line 31 – 41: This is for use in correcting the position and elevation of the CCD camera 10, which change owing to change in the attitude (pitch angle) of the vehicle during acceleration or deceleration. Specifically. this is achieved by mounting height sensors at the four corners of the vehicle (these sensors are omitted from FIGS. 1 and 2), determining the positional relationship between the vehicle and the road surface, and using the information obtained to correct the camera elevation, thereby preventing errors in mapping calculations between coordinates in the image and coordinates in the actual plane coordinates.).
Regarding claim 6, the Kuramoto and Nakayama combination teaches the method according to claim 5.
Additionally, Kuramoto teaches wherein the object distance estimation step includes an object location calculation process of confirming the object included in the two-dimensional image (Figure 7 and 8, Detected Objects; Page 463, Column 1, Section IV: In Scenario-A, the reliability of the road plane assumption was confirmed as illustrated in Fig. 7. Five parked vehicles exist in front of the ego vehicle as shown in Fig. 7a. Because of the static environmental conditions and due to some noise in the data association techniques, MWR and LIDAR detect only the closest car whereas the enhanced SSD detects the five cars with providing the relevant bounding rectangles.), and estimating a direction and a distance to the object based on the three-dimensional coordinate value corresponding to the each pixel (Figure 2, 5, and 8; Page 461, Column 1, ¶ 1: After these calculation, each pixel on image has depth at the moment as shown in Fig. 4.; Page 461, Column 1, Section D: Object in WCS is described by a state vector
X
^
=
[
p
x
w
,
p
y
w
,
p
˙
x
w
,
p
˙
x
w
,
p
¨
x
w
p
¨
x
w
]
T
which contains the values of position, velocity and acceleration values in x and y directions, respectively. A measurement vector of the object position in the image domain is expressed by
Z
^
=
[
u
,
v
]
T
.).
Regarding claim 7, the Kuramoto and Nakayama combination teaches the method according to claim 6.
Additionally, Kuramoto teaches wherein at the object distance estimation step, the distance to the object is estimated using a three-dimensional coordinate value corresponding to a pixel corresponding to the ground of the object included in the two-dimensional image (Figure 2; Page 460, Column 1, Section A: Therefore, the object position is regarded to be indicated by the 2D bottom center (u, v) of its rectangle in this study.; Page 461, Column 1, Section D: Object in WCS is described by a state vector
X
^
=
[
p
x
w
,
p
y
w
,
p
˙
x
w
,
p
˙
x
w
,
p
¨
x
w
p
¨
x
w
]
T
which contains the values of position, velocity and acceleration values in x and y directions, respectively. A measurement vector of the object position in the image domain is expressed by
Z
^
=
[
u
,
v
]
T
.).
Regarding claim 8, Kuramoto teaches a method of an autonomous vehicle for estimating a distance to an object captured by a mono camera of the autonomous vehicle (Abstract: This paper proposes an approach to calculate 3D positions of far detected vehicles. Mainly, the distance from the vehicles during autonomous driving must be estimated precisely to strategize a safe path planning.), the method comprising:
a two-dimensional image acquisition step of acquiring a two-dimensional image of the object captured by the mono camera (Figure 2; Page 459, Column 2, ¶ 5: In this paper, we propose a framework for detecting far objects and estimating the corresponding distance to the vehicle using mono-camera and GNSS/IMU system.), wherein the mono camera is installed in parallel to a ground the autonomous vehicle is travelling (Page 460, Column 1, Section II: The image is captured by a front camera and inputted to a trained DCNN.)
a pixel coordinate estimate step of estimating a three-dimensional coordinate value for at least some of pixels of a two-dimensional image of the object with respect to a ground of the two-dimensional image of the object captured by the mono camera based on at least the height of the mono camera (Figure 2 and 3; Page 460, Column 2, Section C: Figure 3 shows the flowchart of estimating the 3D object position in WCS from CCS… Accordingly, a 3D position of an object in CCS = cp = (cp-x, cp-y,, cp-z), can be described as follows:
PNG
media_image1.png
67
326
media_image1.png
Greyscale
As the object is assumed the be in the road plane, (3) can be rewritten to (4).
PNG
media_image2.png
79
308
media_image2.png
Greyscale
);
a coordinate system matching step of matching each pixel of the two-dimensional image and a three-dimensional coordinate system (Figure 2 and 3; Page 460, Column 2, Section C: Figure 3 shows the flowchart of estimating the 3D object position in WCS from CCS… Accordingly, a 3D position of an object in CCS = cp = (cp-x, cp-y,, cp-z), can be described as follows:
PNG
media_image1.png
67
326
media_image1.png
Greyscale
As the object is assumed the be in the road plane, (3) can be rewritten to (4).
PNG
media_image2.png
79
308
media_image2.png
Greyscale
);
a semantic information location estimation step of estimating a three-dimensional coordinate value of semantic information for autonomous driving included in the ground of the two-dimensional image (Page 459, Abstract: This paper proposes an approach to calculate 3D positions of far detected vehicles. Mainly, the distance from the vehicles during autonomous driving must be estimated precisely to strategize a safe path planning.; Page 461, Column 1, Section D: As the distance estimation of far objects is a main objective, the image region closer to the horizon curve has a larger difference between adjacent pixels as shown in Fig. 4… Object in WCS is described by a state vector
X
^
=
[
p
x
w
,
p
y
w
,
p
˙