US 11,657,592 B2
Systems and methods for object recognition
Xinyi Ren, Hangzhou (CN); Feng Wang, Hangzhou (CN); Haitao Sun, Hangzhou (CN); and Jianping Xiong, Hangzhou (CN)
Assigned to ZHEJIANG DAHUA TECHNOLOGY CO., LTD., Hangzhou (CN)
Filed by ZHEJIANG DAHUA TECHNOLOGY CO., LTD., Zhejiang (CN)
Filed on Jun. 24, 2021, as Appl. No. 17/304,742.
Application 17/304,742 is a continuation of application No. PCT/CN2018/123775, filed on Dec. 26, 2018.
Prior Publication US 2021/0357656 A1, Nov. 18, 2021
Int. Cl. G06V 10/44 (2022.01); H04N 7/18 (2006.01); G06V 20/52 (2022.01); G06V 30/413 (2022.01); G06V 10/75 (2022.01); G06V 10/52 (2022.01)
CPC G06V 10/44 (2022.01) [G06V 10/52 (2022.01); G06V 10/759 (2022.01); G06V 20/52 (2022.01); G06V 30/413 (2022.01); H04N 7/183 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A system for object recognition, comprising:
at least one storage medium including a set of instructions; and
at least one processor in communication with the at least one storage medium, wherein when executing the set of instructions, the at least one processor is directed to cause the system to:
obtain an image including a search region;
obtain a model including a plurality of feature points;
determine, for each of one or more sub-regions of the search region, a match metric indicating a similarity between the model and the sub-region of the search region, the match metric at least correlating with the amount of feature points that satisfy a condition, wherein to determine a match metric indicating a similarity between the model and the sub-region of the search region, the at least one processor is directed to cause the system to:
for each of the plurality of feature points,
determine a similarity value between the feature point and a point in the sub-region; and
designate the feature point as a similar point as the point in the sub-region in response to a determination that its similarity value is above a threshold; and
designate the amount of the similar points as a representation of the match metric; and
determine, among the one or more sub-regions of the search region, an instance of the model based on the match metrics.