Weak supervision target detection method and system

Abstract

The invention discloses a weak supervision target detection method and a weak supervision target detection system, which are used for training a target detector to detect a target in a picture under the condition of only annotation of an image category, and can save a large amount of manpower, material resources and financial resources consumed by annotation information. In the prior frame generation part, a selective search algorithm and a gradient weighted class activation mapping method are combined to generate a better prior frame, and meanwhile, in the optimization iteration process of a detector, supervision information of low-level features is added, and the concept of likelihood is introduced to measure the degree that a target in the prior frame is a complete target. The problem that a current weak supervision target detection method is prone to falling into a local optimal pain point, so that a network tends to select a prior frame covering a whole target under the condition that no target bounding box information supervision exists is solved. The network improves the performance of weak supervision target detection, and can be used in the fields of automatic driving, intelligent security and protection and the like; experimental results show that the method has good competitive performance.

Description

technical field [0001] The invention belongs to the technical field of computer vision image processing, and in particular relates to a weakly supervised target detection method and system. Background technique [0002] The purpose of weakly supervised object detection is to train an object detector in the case of only image level labeling, which is different from the need for instance level (instance level), which needs to label the center coordinates of the largest circumscribed rectangle of the object in the image, height and width) annotations for fully supervised object detection. Labeling instance-level information requires a lot of manpower, material and financial resources. However, the cost of labeling with image categories is obviously lower, and we can also crawl a large number of images with category annotations from web search engines, social media, etc. A large amount of training data can improve the performance of object detection. Obviously, these cheap and...

AI Technical Summary

Problems solved by technology

[0004] At the same time, since there is no instance-level rectangular label information, the current methods use a large number of object proposals to ensure the recall rate, which will lead to a lot of noise in the proposal frame (a small part of the object, the background, etc. ), will not only lead to unstable training, but also consume a lot of GPU computing resources

Images