白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Image processing apparatus, image processing system, and image processing method

專利號
US10867166B2
公開日期
2020-12-15
申請人
SONY CORPORATION（JP Tokyo）
發(fā)明人
Kazuhiro Shimauchi; Takashi Kohashi; Masakazu Ebihara; Yuji Ono; Hidetoshi Nagano
IPC分類
G06K9/00; G06T7/215; G06T7/292; G06K9/62; G06T7/20
技術領域
person,detection,candidate,in,image,frame,moving,body,process,point
地域： Tokyo

摘要

Provided are an apparatus and a method for executing a person detection process from an image. A divisional small region setting window is set and an image in the window is determined to be a person based on the number of moving body pixels of each divisional small region, and a first person candidate point is set in the window when the image is determined to be a person. A person determination process is executed based on an image feature quantity in a person determination detection frame, and a second person candidate point is set in the person determination detection frame when it is determined to be a person. A distribution state in a moving body detection frame of the person determination detection frame is analyzed, and an image in the person determination detection frame is determined to be a person based on an analysis result.

說明書

As described above, there occurs a difference in that, in a case in which the moving body is a person, the moving body detection frame in which the “second person candidate point” is detected is set densely in the horizontal direction, and in a case in which the moving body is not a person, the moving body detection frame in which the “second person candidate point” is detected is not set densely in the horizontal direction.

The erroneous detection removal process in steps S303 and S304 is executed as the process of deleting the erroneously detected “second person candidate point” on the basis of the difference.

A lightweight arithmetic process for realizing the process of detecting and deleting the erroneous detection will be described with reference to FIG. 27.

FIG. 27 illustrates a moving body detection frame 350 serving as the processing target, examples of a plurality of determination detection frames in which the “second person candidate point” is assumed to be detected, and a person determination detection frame p1 371 to a person determination detection frame p5 375.

The person determination detection frames 371 to 375 are frames set in the process of step S103 of the flow of FIG. 6, that is, in the second person detection process executed in accordance with the flow illustrated in FIG. 17. These are the person determination detection frames described with reference to FIGS. 18 to 20.

權利要求

1
微信群二維碼
意見反饋