Target detection method, system and apparatus for object with large length-width ratio, and medium

Abstract

The invention relates to the technical field of target detection, in particular to a target detection method, system and apparatus for an object with a large length-width ratio, and a medium. The method comprises the following steps: acquiring a to-be-detected target image; inputting the to-be-detected target image into a trained target detection model, wherein a loss function of the trained target detection model comprises a length loss value of a long side of an object and a central position loss value of the long side of the object; outputting the position of each object in the target image and a plurality of category probability values; and determining a final category of each object according to the plurality of category probability values. According to the target detection method for the object with the large length-width ratio, the central position loss value of the long side of the object and the length loss value of the long side of the object are additionally added into the loss function, so that the model is guided to improve the detection performance of the object with the large length-width ratio, and the target detection precision and efficiency are improved.

Description

technical field [0001] The present application relates to the technical field of target detection, and more specifically, the present application relates to a target detection method, system, device and medium for objects with a large aspect ratio. Background technique [0002] Object detection is an important research direction of computer vision and digital image processing, and it is widely used in robot navigation, intelligent video surveillance, industrial inspection, aerospace and many other fields. The goal of object detection is to find the object of interest in the image, including two subtasks of object location and object classification, that is, to determine the category and location of the object at the same time. [0003] At present, the target detection mode that uses neural networks combined with a large amount of image data for training has become the mainstream method in the industry. Algorithms based on neural networks can basically be classified into two...

AI Technical Summary

Problems solved by technology

In some cases, the network cannot detect objects with a large aspect ratio. In other cases, although the network can detect objects with a large aspect ratio, the target position is not accurate enough, especially the long side of the object is not detected accurately.

In addition, from the detection results, many existing methods have large errors on the long side of the target, which further confirms the shortcomings of IoU loss.

Images