Object detection method and device

Abstract

The invention provides an object detection method and a device. The object detection method comprises steps that: disparity images are acquired from a stereo camera for object area imaging; planes are detected from the disparity images; object surface candidates are selected from the planes detected from the disparity images according to characteristics of a physical surface of an object; the object surface candidates are converted into front view surfaces, and the front view surfaces are object surface images acquired by utilizing the stereo camera to shoot from a visual angle just pointing to the physical surface of the object; the object is detected at least partially on the basis of the front view surfaces after conversion. According to the method and the device, influence of original deformation can be eliminated, the object is detected by utilizing already-extracted non-deformation characteristics and / or a classifier and on the basis of the front view surfaces after conversion.

Description

technical field [0001] The present invention generally relates to image processing, and more particularly relates to a method and device for object detection based on disparity map image processing. Background technique [0002] Many methods for detecting objects based on disparity images have been developed, such as detecting vehicles, fences, etc. on the road based on disparity images. [0003] However, sometimes, due to factors such as the performance limitation of the camera or the characteristics of the scene itself, a disparity map with relatively sparse disparity points may be obtained, which is called a sparse disparity map hereinafter. Due to the sparse disparity map effect, it may be difficult to detect objects such as vehicles etc. Moreover, in practice, it is often necessary to project the original disparity map horizontally or vertically to obtain a U disparity map or a V disparity map, and then perform object detection on the U disparity map or V disparity map...

AI Technical Summary

Problems solved by technology

Due to the sparse disparity map effect, it may be difficult to detect objects such as vehicles, etc.

Moreover, in practice, it is often necessary to project the original disparity map horizontally or vertically to obtain a U disparity map or a V disparity map, and then perform object detection on the U disparity map or V disparity map. Occlusion caused by V projection or weak object features on U or V disparity maps due to sparse disparity points, making it difficult to detect objects

Images