Wang Lin

TL;DR: In this paper, a demographic statistics device and method based on boundary selection, which belongs to the field of deep learning and image processing, is revealed, and consists of the following steps of by improving the YOLO neural network by increasing the division of the yOLO unit from 7*7 to 9*9, that is, increasing the number of detections per unit to three, and then replacing the yolo PCneural network with the fire module in SqueezeNet; replacing The 16th, 18th, and 24th 3*3 convolutional

TL;DR: In this paper, a real-time target detection method for computing resource limited platform deployment, which belongs to the field of deep learning and image processing, is presented, where the first five convolution layers and pooling layers of YOLO-v3-tiny and the prediction of two different scales, a Fire modulein the SqueezeNet is introduced, and a 1 * 1 bottleneck layer is connected with the Dense, so that the structure can be operated on an embedded AI platform in real time.

TL;DR: Li et al. as mentioned in this paper improved YOLO-v3-tiny neural network by adding fire modules in SqueezeNet, 1×1 bottleneck layers, and dense connection to achieve smaller, faster, and more lightweight network that can be run in real time on an embedded AI platform.

TL;DR: In this article, a real-time object detection method deployed in a platform having a limited computing resource is proposed, which comprises: forming a Tinier-YOLO structure by means of improving on a YOLO-v3-tiny neural network, wherein the Tinier structure retains the first five convolutional and pooling layers, and incorporates fire modules, a 1*1 bottleneck layer, and dense connection in SqueezeNet.