Estimating pedestrian proximity using MiDaS and YOLOv7

As the field of computer vision continues to advance, there is an increasing need to accurately estimate the proximity of pedestrians and objects in real-world scenarios. One promising approach to achieving this goal is through the use of MiDaS monocular depth estimation, combined with detections made using the YOLOv7-pose model. MiDaS is a deep learning-based method for estimating the depth of an image, using a single RGB input. Meanwhile, YOLOv7-pose is a state-of-the-art object detection and pose estimation algorithm that can accurately identify the location and orientation of people and objects in an image. By combining these two powerful techniques, it is possible to estimate the distance between a camera and pedestrians or objects, enabling a wide range of applications in fields such as autonomous vehicles, robotics, and surveillance. <a href="https://medium.com/@jaimin-k/estimating-pedestrian-proximity-using-midas-and-yolov7-14b5a08b8740">Read More</a>