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 .
Claim Objections
Claims 6-7 and 15-16 are objected to because of the following informalities: “optimised”. It should be corrected to state “optimized”. Appropriate correction is required.
Claim 7 and 16 are objected to because of the following informalities: “one or more environmental conditions consisting of time, weather and location”. It is disclosed later in the claim to “determine one or more environmental conditions…” There cannot be “one or more” conditions if the conditions consist of “time, weather, and location.” For purposes of examination, the Examiner will interpret the environmental conditions to be “time, weather, or location”.
Claim 8 and 17 are objected to because of the following informalities: “and/or”. It cannot be both. For purposes of examination, Examiner is interpreting this to be an “or”. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 4 and 13 recite the limitation “a predefined crowd density range” in the last sentence of the claim. It is unclear since a predefined crowd density range is the same as the predefined crowd density range from claim 1, as the image segments are the same from claim 1.
Claim Rejections - 35 USC § 103
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 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, 6, 9, 10, 15, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over GANG YIN CN-116311084-A, hereinafter YIN, in further view of Haroon Idrees US-20180005071-A1, hereinafter Idrees.
As per claim 1, YIN discloses a crowd counting system, the system comprising: at least one processor (see YIN page 4/42, wherein a processor is disclosed); and at least one memory including computer program code (see YIN page 5/42, wherein a program stored in memory is disclosed); wherein the at least one processor, at least one memory and the computer program code are configured to allow the system to (see YIN page 5/42, wherein the memory, processor, and code are used to execute the application): receive an image depicting a crowd (see YIN page 6/42, wherein a video image is collected. The video image is a target image which comprises a detection area. The detection area comprises a crowd as disclosed on page 7/42 and FIG. 4); determine if a crowd density variation exists within the image based on a predetermined threshold for crowd density variation (see YIN page 6/42, wherein a probability of crowd aggregation in the area is calculated using a preset probability threshold); in response to a positive determination of the crowd density variation (see YIN middle of page 8/42, wherein the judgement of crowd aggregation occurs); partition the image into a plurality of image segments (see YIN page 8/42, wherein the detection area is divided into a plurality of detection sub-regions);determine a crowd size within each image segment (see YIN page 9/42, wherein a crowd density is calculated for each detection sub-area) using a crowd counting algorithm of the image segment (see YIN page 9/42, wherein the number of people’s heads in the crowd density of a sub-section is calculated as
N
t
o
t
a
l
(
i
)
); and determine the crowd size in the image by summing the crowd size in each of the plurality of image segments (see YIN page 11/42, wherein the determination of crowd gathering, which includes crowd count, or size, is performed by counting the number of heads in each detection area, i.e., image segments).
However, YIN fails to explicitly disclose where Idrees teaches:partition the image into a plurality of image segments based on predefined crowd density ranges, each image segment corresponding to a predefined crowd density range (see Idrees ¶66-70, wherein the image is partitioned into crowd patches, each corresponding to a range of “crowd patch” or “non-crowd patch” using a log-likelihood, meaning each patch has a crowd or doesn’t);determine a crowd size within each image segment using a crowd counting algorithm associated with crowd density range of the image segment (see Idrees ¶67-69, wherein counts are estimated independently for each patch using a spatial Poisson counting process, i.e., crowd counting algorithm. These patches also include the crowd and non-crowd density frequencies), wherein each predefined crowd density range is associated with a respective crowd counting algorithm (see Idrees ¶68-70 and FIGS. 4A-4B, wherein crowd density frequencies, i.e., density ranges, are used to determine crowd and non-crowd patches of the image).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify YIN’s system by using Idrees’s teaching by including a predefined crowd density range to the plurality of image segments in order to acquire a more accurate determination of the crowd size that corresponds to the crowd density.
As per claim 6, YIN, in combination with Idrees, discloses the crowd counting system as claimed in claim 1, wherein each predefined crowd density range is determined based on the crowd counting algorithm optimized for accuracy within said crowd density range (see Idrees ¶67-69, wherein counts are estimated independently for each patch using a spatial Poisson counting process. The modeled Poisson R.V. is used to identify the crowd patches as a crowd or non-crowd using the log-likelihood
φ
(P) ratio with an expected value of
λ
i
+
).
As per claim 9, YIN, in combination with Idrees, discloses the crowd counting system as claimed in claim 1, wherein the image comprises a video frame depicting the crowd, the video frame being one of a plurality of video frames extracted from a video stream (see YIN page 6/42, wherein a video monitoring device includes a camera that is used for acquiring video images).
As per claims 10, 15, and 18, the rationale provided in claims 1, 6, and 9 are incorporated herein. In addition, the method of claims 10, 15, and 18 correspond to the system of claims 1, 6, and 9.
Claims 2-4 and 11-13 are rejected under 35 U.S.C. 103 as being unpatentable over YIN, in combination with Idrees, in further view of Yaoxuan Yuan Estimating Crowd Density in an RF-Based Dynamic Environment, hereinafter Yuan.
As per claim 2, YIN, in combination with Idrees, discloses the crowd counting system as claimed in claim 1, wherein to determine if a crowd density variation exists within the image, the system is configured to: divide the image into a plurality of tiles (see YIN page 9/42 and FIG. 7, wherein the detection area is divided into N parts); determine a crowd density of each tile using a density classification algorithm (see YIN page 9/42, wherein crowd density of a sub-section is calculated as
λ
N
t
o
t
a
l
(
i
)
S
a
r
e
a
(
i
)
).
However, YIN, in combination with Idrees, fails to explicitly disclose where Yuan teaches:compare a variation of the determined crowd densities against the predetermined threshold for crowd density variation (see Yuan page 4-5/9, wherein a deviation, which is the RSSI variance of crowd density, is compared against a threshold
ε
for variation errors).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify YIN’s, in combination with Idrees, system by using Yuan’s teaching by including a threshold comparison to the crowd densities in order to further verify if a crowd is truly detected or if there was a counting error.
As per claim 3, YIN, in combination with Idrees and YUAN, discloses the crowd counting system as claimed in claim 2, wherein to divide the image into a plurality of tiles (see YIN page 9/42 and FIG. 7, wherein the detection area is divided into N parts), the system is configured to: divide the image into the plurality of tiles with an overlap between edges of adjacent tiles (Idrees ¶71 that the patches are overlapped. See further Idrees ¶74 and FIG. 5, wherein an overlap between adjacent edges is shown).
As per claim 4, YIN, in combination with Idrees and Yuan, discloses the crowd counting system as claimed in claim 2, wherein to partition the image into the plurality of image segments, the system is configured to: partition the image along edges of the plurality of tiles into the plurality of image segments (see Idrees ¶74 and FIG. 5, wherein the image is split along the edges of the patches, into the patches of the lower layers) based on the predefined crowd density ranges (see Idrees ¶66-70, wherein the image is partitioned into crowd patches, each corresponding to a range of “crowd patch” or “non-crowd patch” using a log-likelihood, meaning each patch has a crowd or doesn’t), wherein each image segment comprises one or more tiles and corresponds to a predefined crowd density range (see Idrees FIG. 5, wherein the 4x4 patches of the next layer correspond to the previous layer’s patch. Additionally, Idrees ¶67 discloses the density for each patch
λ
|
P
|
).
As per claims 11-13, the rationale provided in claims 2-4 are incorporated herein. In addition, the method of claims 11-13 correspond to the system of claims 2-4.
Claims 5 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over YIN, in combination with Idrees and YUAN, in further view of Kun-lin YANG CN-110348537-B, hereinafter YANG, and GANG CHEN CN-110188597-B, hereinafter CHEN.
As per claim 5, YIN, in combination with Idrees and YUAN, fails to explicitly disclose where YANG teaches:The crowd counting system as claimed in claim 2, wherein to divide the image into a plurality of tiles, the system is configured to divide the image into a first set of tiles at a first resolution and a second set of tiles at a second resolution (see YANG page 6/45, wherein the image is split into a first and second set of sub-feature images. It is further disclosed in YANG page 7/45 that the resolutions between each sub-feature is at a different resolution).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify YIN’s, in combination with Idrees and YUAN, system by using YANG’s teaching by modifying the plurality of tiles to a first and second set of tiles at a first and second resolution in order to further test the system to be able to count at various resolutions.
However, YIN, in combination with Idrees, YUAN, and YANG, fails to explicitly disclose where CHEN teaches:wherein to determine the crowd size in the image, the system is configured to determine the crowd size in the image by averaging the summed crowd size associated with the first set of tiles and the summed crowd size associated with the second set of tiles (see CHEN page 7/20, wherein the locating and counting branch are fused and averaged in order to obtain the final crowd counting value. The locating and counting branches are different from each other, as described in page 6/20, and contains cut regions of the crowd, i.e., a plurality of tiles, as disclosed on page 3/20).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify YIN’s, in combination with Idrees, YUAN, and YANG, system by using CHEN’s teaching by including the averaged summed crowd size to the first and second set of tiles in order to further verify the crowd counting against each set to improve accuracy of the crowd counting.
As per claim 14, the rationale provided in claim 5 is incorporated herein. In addition, the method of claim 14 corresponds to the system of claim 5.
Claims 7 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over YIN, in combination with Idrees, in further view of CHANG-AN WANG CN-112560829-B.
As per claim 7, YIN, in combination with Idrees, fails to explicitly disclose where WANG teaches:The crowd counting system as claimed in claim 1, wherein each crowd counting algorithm is optimized for one or more environmental conditions consisting of time, weather and location (see WANG page 17/57, wherein the crowd counting includes the calculation for a traffic location in real time); and wherein to determine the crowd size within each image segment, the system is configured to: determine one or more environmental conditions of the image or the image segment (see WANG bottom of page 16/57, wherein the traffic place of the crowd image is detected, as in determined, in real time); and determine the crowd size within each image segment using a crowd counting algorithm (see WANG page 17/57, wherein the crowd size in each sub-area is determined) associated with crowd density range of the image segment and the one or more determined environmental conditions of the image or the image segment (see WANG bottom of page 16/57, wherein the traffic place of the crowd image is detected, as in determined, in real time).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify YIN’s, in combination with Idrees, system by using WANG’s teaching by including environmental conditions to the crowd counting algorithm in order to additionally consider the effect of the environment on the crowd.
As per claim 16, the rationale provided in claim 7 is incorporated herein. In addition, the method of claim 16 corresponds to the system of claim 7.
Claims 8 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over YIN, in combination with Idrees, in further view of Tao LEI CN-116740439-A, hereinafter LEI.
As per claim 8, While YIN, in combination with Idrees, discloses “one or more of the plurality of image segments,” it fails to explicitly disclose where LEI teaches:The crowd counting system as claimed in claim 1, wherein the system is further configured to upsample the image depicting a crowd before determining the crowd density variation and/or the image before determining the crowd size (see LEI page 3/32, wherein the image comprising a crowd is upsampled before obtaining the crowd size).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify YIN’s, in combination with Idrees, system by using LEI’s teaching by including upsampling to the crowd image, which includes one or more of the plurality of image segments, in order to acquire a more detailed resolution for crowd counting.
As per claim 17, the rationale provided in claim 8 is incorporated herein. In addition, the method of claim 17 corresponds to the system of claim 8.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Bradley Obas Felix whose telephone number is (703)756-1314. The examiner can normally be reached M-F 8-5 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, Vincent Rudolph can be reached at 5712728243. 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.
/BRADLEY O FELIX/Examiner, Art Unit 2671
/VINCENT RUDOLPH/Supervisory Patent Examiner, Art Unit 2671
Prosecution Insights