Improved convolutional neural network-based object detection device and method

Abstract

The invention provides an improved convolutional neural network-based object detection method. The method comprises the following steps of: acquiring a mark image of a marked object; preliminarily training an improved convolutional neural network by adoption of a random sampling method, obtaining preliminarily classified positive samples and negative samples and corresponding classification probability values, and selecting a certain proportion of positive samples and negative samples according to the classification probability values to train the improved convolutional neural network so as toobtain a trained object detection model; inputting a to-be-detected image; and carrying out object detection on the to-be-detected image by adoption of the object detection model and outputting a detection result. Compared with the prior art, the method is capable of rapidly and correctly realizing object detection in images.

Description

technical field [0001] The invention relates to image processing, video monitoring and security protection, in particular to an object detection device and method. Background technique [0002] Object detection is a technology that uses computers to process, analyze, and understand images to detect objects in various patterns. At present, object detection technology has a huge commercial market and good application prospects in Internet application products such as intelligent transportation, image search, product recommendation, user behavior analysis and face detection. It has broad application prospects in high-tech industries such as biology, medicine and geology and many other disciplines. [0003] Early object detection technology mainly used feature extraction methods such as scale-invariant feature transform (SIFT) and histogram of oriented gradients (HOG), and input the extracted features into the classifier for classification detection. These features are manual...

AI Technical Summary

Problems solved by technology

[0005] "Rich Feature Hierarchies for Accurate Object Detection and SemanticSegmentation. R Girshick, J Donahue, T Darrell, J Malik. Computer Vision & Pattern Recognition, 2013:580-587" discloses an R-CNN-based accurate object detection and segmentation method, but the calculation The amount is too large to detect in real time

"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. K He, X Zhang, S Ren, J Sun. "IEEE Transactions on Pattern Analysis & Machine Intelligence", 2014,37(9):1904-16" discloses a method based on SPP-net (Spatial Pyramid Pooling Convolutional Neural Network) image recognition method, which reduces the possibility of overfitting in the training process, but the implementation process is more complicated, and the time cost and space cost are higher

"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. S Ren, K He, R Girshick, J Sun. "IEEE Transactions on Pattern Analysis & Machine Intelligence", 2016:1-1" discloses a method based on Faster R- CNN's object detection method, which improves the accuracy of the algorithm through multi-task loss learning, but the training takes a long time

Images