To meet the requirements of automation and intelligence of the vehicle-sighting system, the paper gives an overview oftwo widely-used target recognition algorithms, including pattern recognition and deep learning. Four typical algorithms,HOG-cascading-Adaboost algorithm and surf combining SVM algorithm, which belong to pattern recognition, CNNnetwork and YOLOv3 network, which belong to deep learning, are elaborated in detail. Different algorithms are used toidentify images in the same test set in the experiment, and the performance of each algorithm is compared from threeaspects, recognition rate, recall rate and recognition time. Finally, it can be concluded that YOLOv3 algorithm is better fortarget recognition when concerning the recognition rate and recall rate, with the recognition rate as high as 95.8% andfewer targets missed. Considering the real-time effect, the pattern recognition algorithm has less recognition time but therecognition rate reduces. Therefore, the recognition time and recognition rate should have a compromise in practicalapplication.
展开▼
