Visual Perception for Self-Driving Cars!
<p>YOLO — <strong>Y</strong>ou <strong>O</strong>nly <strong>L</strong>ook <strong>O</strong>nce is a family of one stage object detection algorithms. The algorithm works by dividing images into grids, and each grid detects and localizes the object it contains. It employs convolutional neural networks (CNN) as a backbone to detect objects in real-time. YOLO models deliver high accuracy, speed and learning capabilities which make them perfect for real-time object detection.</p>
<p>Recently, <a href="https://github.com/WongKinYiu/yolov7" rel="noopener ugc nofollow" target="_blank">YOLOv7 is announced</a> and it surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher, making the model state-of-the-art real-time object detectors for Self-Driving cars. That is the reason why we chose YOLOv7 as our target model.</p>
<p><a href="https://medium.com/@shahrullo/visual-perception-for-self-driving-cars-bb500f8c6adc"><strong>Website</strong></a></p>