YOLO target detection method using OpenCL

Abstract

The invention discloses a YOLO target detection method using GPU hardware acceleration. The method comprises steps of: (1) initializing a convolutional neural network (CNN); (2) acquiring a training sample; (3) determining the grids of the training sample; (4) training the CNN; (5) determining whether a loss value is less than 0.01, saving the trained CNN if so, or acquiring and training a next training sample if not; (6) saving the model of the trained CNN in a computer hard disk; (7) extracting the characteristics of a test picture; (8) determining the location rectangular frame of the testpicture target; and (9) ending the target detection. The method can realize feature extraction on a target in the image on a general computer, then marks the location of the target with the location rectangular frame, and marks the category of the target at the upper right corner of the location rectangular frame.

Description

technical field [0001] The invention belongs to the field of computer technology, and further relates to a YOLO (YouOnly Look Once) object detection method accelerated by an open computing language OpenCL (Open Computing Language) in the field of computer vision and deep learning technology. The invention can accelerate the YOLO target detection method based on the deep convolutional neural network, and can be used on a general-purpose computer to realize real-time detection of the target in the picture. Background technique [0002] Object detection methods with high speed and high performance are the core technologies in the field of computer vision. In recent years, based on deep convolutional neural network, it has shined in the field of computer vision. Compared with traditional methods, image classification and target detection algorithms based on deep convolutional neural network have significantly improved classification and recognition accuracy. For target detectio...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that the method of manually selecting features, which only calculates the integral map and the square integral map, does not have good generalization ability for more complex scenes, and the detection accuracy is low.

Images