Although the model has an excellent detection performance, it is also a computationally intensive algorithm. The backbone network of YOLOv4 is computationally complex, which requires a large amount of storage s
Stage one (PDNet-1) used a YOLOv3 [119] detector with an AlexNet feature extractor to predict leaf bounding boxes. Stage two (PDNet-2) was made up of a 32-layer residual CNN architecture, global average pooling layer, a 42-way fully connected layer and a softmax layer to perform ...
To employ effective drogue detection in the air, a deep convolutional neural network-based single-stage detector algorithm, YOLOv4-tiny, is applied. Furthermore, to track the moving drogue in the air simultaneously, a point cloud-based tracking algorithm with an RGB-D camera system is developed...
we designed an automated drone detection system using YOLOv4. The model was trained using drone and bird datasets. We then evaluated the trained YOLOv4 model on the testing dataset, using mean average precision (mAP), frames per second (FPS), precision, recall, and F1-score as evaluation par...
Furthermore, our results demonstrated the potential of using YOLOv4 for automated bird detection and monitoring in the wild, which could help conservationists better understand bird populations and identify potential threats.doi:10.3390/app13137787Mpouziotas, Dimitrios...
For example, YOLO [2], a one-stage object detection model, enables real-time object detection by delivering input images simultaneously to an efficient backbone network. YOLO has since developed into a more efficient and accurate model, YOLOv4 [5], and is being used in various fields such ...