Recognition method based on Green Associative Mechanism for weak contrast vehicle targets

详细信息    查看全文

• 作者：Dongyao Jia ; ^{bjtujdy@126.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Huaihua ZhuAuthor Vitae ; Shengxiong ZouAuthor Vitae ; Ke HuangAuthor Vitae
• 关键词：Visual perception theory ; Weak contrast vehicle target ; Green Association Mechanism ; Green Neuron-interactive Association Network
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：26 August 2016
• 年：2016
• 卷：203
• 期：Complete
• 页码：1-11
• 全文大小：6097 K

文摘

As nowadays haze and other inclement weather becomes frequency, weak contrast vehicle target recognition has become a problem needed to solve urgently. At present, the existing vehicle recognition algorithms for weak contrast target vehicle are hard to achieve ideal effect. Therefore, in this paper, the Green Associative Mechanism Model based on human vision perceptual theory is proposed. This model has excellent associative function which is improved by introducing the neural interaction mechanism. Then, associative WHAT pathway used for object recognition in human visual cortex is abstracted properly. And on this basis a hierarchical Associative Mechanism Model is established, which is used for weak contrast vehicle recognition. The experiments show that the recognition rates of the model reach 88.6%, which is far above these of the existing recognition algorithms.