A training method to improve the effect of small target detection

Deep learning target detection has always been a major research direction in the field of artificial intelligence. Its research results are widely used in the fields of automatic driving, security system and medical treatment. This paper proposes a method to improve the detection effect of small targets, which realizes the detection of objects of different scales in the input image, especially to improve the detection effect of small-scale targets. Before the collected data set is sent to the neural network for training, it is first divided into three different scales according to the size of the target to be detected in the image of the data set. Then one or several images in the large target data set are stitched, the images in the small target data set are enlarged, and the above two types of images are used to form a new data set. Finally, the new data set and the original data set are sent to the neural network for training. In this paper, the YOLOX target detection network is used for verification. The results show that the detection effect of the network obtained by this method on small targets has been improved, and the missed detection rate has been reduced from 31.2% to 27.5%. At the same time, the detection effect of large and medium-sized targets has not been sacrificed.