Object detection in a camera sensing system has been addressed by researchers in the field\nof image processing. Highly-developed techniques provide researchers with great opportunities\nto recognize objects by applying different algorithms. This paper proposes an object recognition\nmodel, named Statistic Experience-based Adaptive One-shot Detector (EAO), based on convolutional\nneural network. The proposed model makes use of spectral clustering to make detection dataset,\ngenerates prior boxes for object bounding and assigns prior boxes based on multi-resolution.\nThe model is constructed and trained for improving the detection precision and the processing\nspeed. Experiments are conducted on classical images datasets while the results demonstrate the\nsuperiority of EAO in terms of effectiveness and efficiency. Working performance of the EAO is\nverified by comparing it to several state-of-the-art approaches, which makes it a promising method\nfor the development of the camera sensing technique.
Loading....