约束性神经网络及在目标方向估计中的应用.pdf

Geomatics Science and Technology 测绘科学技术, 2018, 6(3), 151-164 Published Online July 2018 in Hans. /journal/gst /10.12677/gst.2018.63017 Constrained Neural Network and Its Application in Target Direction Estimation * Jin Liu, Shumin Liu , Gao Fang State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan Hubei th th th Received: Jun. 11 , 2018; accepted: Jun. 28 , 2018; published: Jul. 5 , 2018 Abstract At present, the mainstream convolutional neural network (CNN) approaches focus on the recogni- tion and positioning of targets in the field of computer vision. Most locate the position of targets with axis-aligned bounding boxes. In order to make a deeper understanding of the images and ob- tain more accurate position of various targets, the direction information is needed. Therefore, a new method is proposed to estimate the target direction, which applies CNN to regress the two di- rectional components of the target direction angle that describes the direction, instead of directly regressing the direction angle like some existing approaches which shows some shortcomings. Considering the function constraint of the square sum of 1 between the directional components, this paper proposes a general method to solve this kind of problems with output constraints by using constrained neural network, which introduces constraint errors into the Loss layer and the back propagation process, and applies it in the target direction estimation. Experiments show that, the target direction estimation method maintains the descent rate and range of the original output loss and moreover, reduce the constraint error