The main task of object detection is to identify and locate interested objects from still images or video sequences. It is one of the key tasks in the field of computer vision. However, the object usually has variable factors in brightness, shape, occlusion and so on, and is interfered by various and complex environmental factors, which makes the research opportunities and challenges of object detection algorithm coexist. In this paper, a main frame of object detection algorithm based on convolutional neural network is studied, which is based on regression. We propose a real-time object detection algorithm based on fully convolution network, which aims to solve the problems of low detection accuracy and poor location accuracy of objects in regression method. The innovation is that the proposed fully convolution network increases the detection flexibility of the model because it is not affected by the input scale. At the same time, we propose a multi feature fusion and multi border prediction strategy, which effectively improves the detection accuracy of small objects. In order to prove the effectiveness of the proposed algorithm, we use PASCAL VOC data set to carry out object detection experiments. In this paper, the accuracy of each object category and the average accuracy of all categories are calculated. Experiments show that the performance of the multi feature fusion algorithm based on the fully convolution network is better than that based on the regression idea such as YOLO, and more than 10% higher than that of the YOLO model.
The main goal of object detection is to recognize and locate the object of interest from the static image or video sequence. It is one of the key tasks in the field of computer vision. However, there are many factors in brightness, shape, color and occlusion of targets, and they are disturbed by complex environmental factors, which make the research opportunities and challenges of object detection algorithms coexist. In this paper, two main frameworks of object detection algorithm based on convolutional neural network are researched, which are based on region proposals and regression idea respectively. Then we present a joint mechanism algorithm for object detection. This algorithm makes a balance between detection efficiency and accuracy to make it more meet the actual needs. The internal of the algorithm is adjusted and optimized, so that the two detectors can make their own judgments according to the characteristics of the image, and decide whether to detect the object to classify and locate it, so that the efficiency is higher and the accuracy is also improved.
Object detection is the basic research direction in the field of computer vision. It provides basic image information data for other advanced computer vision processing and analysis tasks. With the continuous breakthrough of deep machine learning technology, especially convolutional neural network model in the field of digital image processing shows a strong ability to extract image features. By choosing the depth separable convolution layer to replace the standard convolution layer used in the traditional model, the number of parameters of CNN network model is compressed. Depth Separable Convolution Layer (DSCL) decomposes the standard convolution layer factor into depth convolution layer and point convolution layer, and extracts and merges image features in two steps to reduce the number of parameters. By introducing a depth-separable convolution layer instead of a standard convolution layer, the number of parameters of the model convolution layer is reduced by 78.1%. We choose image feature pyramid network to fuse the image features extracted from each layer of CNN network, so that the target detection model can use matching image fusion features for different size and shape of the target to be detected. The average detection precision on the PASCAL VOC dataset increased to 77.5%.