RecoMadeEasy ® Object Detection Applied on a Youtube Video on Streets of Beijing -- Demo 20211116
This demo was run at 15 frames per second detection rate in realtime on a Lenovo laptop all locally with no aid of any external computation aid. It uses the RecoMadeEasy ® Small Object Detection model. The object detection is done on every frame of the original video in realtime. The output is in the form of a JSON file which is shown at the bottom of the clip. The top match for all objects with a posterior probability higher than 20%, including the predicted size and location of the objects, are shown in boxes with the label printed on top. The original video that was used to run this detection is at the following link: • CHINA I Beijing I Street Scenes