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

Next, a specific process executed by the image processing apparatus (camera) will be described.

FIG. 6 is a flowchart illustrating a processing sequence of the person detection process from the captured image executed by the image processing apparatus (camera).

In the person detection process of the present disclosure, since personal detection based on image analysis can be performed even by a camera with a relatively low data processing function as well as an information processing apparatus with a high data processing function such as a PC, a significant reduction in computation which is necessary in the person detection process is implemented.

For example, in a case in which an attempt to perform the person detection from the captured image of the camera is made, in a general process of a related art, a feature quantity is calculated for each pixel constituting image, and a collation process of the calculated feature quantity and a learning dictionary in which feature data of an image of a person is registered is performed.

The feature quantity calculation process and the dictionary collation process are generally performed for all pixels in an image or all pixels in which the moving body is detected and are factors of increasing a processing load.

Further, persons of different sizes are photographed in a captured image in accordance with a distance from the camera. In order to detect image region of persons of various sizes, it is necessary to convert an image to images of different resolutions and carry out a collation process with a dictionary hierarchically for each of images of different resolutions.

權利要求

1
微信群二維碼
意見反饋