{"id":49,"date":"2020-10-03T20:20:45","date_gmt":"2020-10-03T20:20:45","guid":{"rendered":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/f20-teamb1\/?p=49"},"modified":"2020-10-03T20:55:36","modified_gmt":"2020-10-03T20:55:36","slug":"echo-gaos-status-report","status":"publish","type":"post","link":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/f20-teamb1\/2020\/10\/03\/echo-gaos-status-report\/","title":{"rendered":"Echo Gao’s Status Update for 10\/3"},"content":{"rendered":"

Computer Vision:<\/strong><\/h3>\n

Compared different Computer Vision libraries (YOLO3, Tiny-YOLO, OpenCV, Tensorflow) and their detection speed & accuracy on PC. Determined to use Tensorflow Lite for the highest frame rate.<\/p>\n

1.YOLO3& Tiny-YOLO<\/h6>\n

You only look once (YOLO<\/em>) is a state-of-the-art, real-time object detection system.\u00a0 \u00a0Tiny-YOLO is a variation of the Yolo object detector. It is much faster than Yolo, yet less accurate.\u00a0For reference, Redmon et al. report ~51-57% mAP for YOLO on the COCO benchmark dataset while Tiny-YOLO is only 23.7% mAP \u2014 less than half of the accuracy of its bigger brothers (Rosebrock, Adrian).We used a pre-trained model from\u00a0https:\/\/pjreddie.com. Then we optimized tiny yolo by letting it only detects person and reduced input resolution from 416×416 to 200×200. However, it still only reaches 3.7 fps on MacOS. (We also tested out printing the mid-x position of the detected person, which is a value we will need for the robot to rotate and move accordingly).<\/p>\n

\"\"<\/p>\n

reference:<\/p>\n

https:\/\/pjreddie.com\/darknet\/yolo\/<\/p>\n

https:\/\/medium.com\/@madhawavidanapathirana\/real-time-human-detection-in-computer-vision-part-2-c7eda27115c6<\/p>\n

https:\/\/stackoverflow.com\/questions\/44674517\/yolo-darknet-detecting-only-specific-class-like-person-cat-dog-etc<\/p>\n

 <\/p>\n

 <\/p>\n

2.OpenCV<\/h6>\n

Haar Cascade Classifier is a popular algorithm for object detection. We used pre-trained Haar cascade models in OpenCV to detect human face in real time. It is the least accurate approach we’d inverstigated.<\/p>\n

\"\"<\/p>\n

reference:<\/p>\n

https:\/\/opencv-python-tutroals.readthedocs.io\/en\/latest\/py_tutorials\/py_objdetect\/py_face_detection\/py_face_detection.html<\/p>\n

Real-time Face Recognition with Python & OpenCV<\/a><\/p><\/blockquote>\n