Construction and Application Research of the Visual Image Obstacle Type Recognition Model Based on the Computer-Expanded Convolutional Neural Network

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left">Light conditions and traffic conditions</td><td class="align_center">Detection of frames</td><td class="align_center">Number of obstacles</td><td class="align_center">Average recognition accuracy (%)</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Normal light simple traffic conditions</td><td class="align_center">12000</td><td class="align_center">15020</td><td class="align_center">95.1</td></tr><tr><td class="align_left">Normal light complex traffic conditions</td><td class="align_center">8000</td><td class="align_center">33840</td><td class="align_center">92.1</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Statistics of detection results under different light and traffic conditions.</div>

Computational Intelligence and Neuroscience

tab2

Table 2

Table 2: Construction and Application Research of the Visual Image Obstacle Type Recognition Model Based on the Computer-Expanded Convolutional Neural Network 

Table 2 | Construction and Application Research of the Visual Image Obstacle Type Recognition Model Based on the Computer-Expanded Convolutional Neural Network 