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.
Recently, convolutional neural network (CNN) has been widely implemented in the compute vision, nature language processing and automatic driving. However, it makes much difficulties to employ the neural network in the embedded system because of the limit of memory storage and the computation bandwidth. To address those limitations, we explore a two-stage approach in neural network compression for the scene, object detection. In this paper, we first propose an effective pruning approach on a trained neural network, and achieve total 81.86%-91.54% sparse rate with the accuracy losing 1-3%. Then we explore the quantization method to apply on the pruned neural network, and propose an adaptive codebook to store the quantized weight parameters and the index of the weight parameters. We utilize the two-stage model compression approach, model pruning and weights quantization, to implement on tiny-YOLO, the state-of-art object detection model, achieving total 41.9-62.7X compression rate with the accuracy loss less than 3.3%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.