guanjianyu / Automatic_Drive_Detection_Mrcnn

Object detection for autonomous car based on Mask-rcnn and coco dataset

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Automatic_Drive_Detection_Tensorflow_Convnet

This is an implemention of Tensorflow detection model zoo on Python 3 and TensorFlow. The project adopts four different models in Model Zoo to detect cars on road in demo video.

This project is built based on Tensorflow Object Detection API and you can view more detail at here

The detection result based on differen models are shown in flowing link videos.

Models in this project

Model name Speed (ms) COCO mAP[^1] Outputs
ssd_mobilenet_v1_coco 30 21 Boxes
faster_rcnn_inception_v2_coco 58 28 Boxes
faster_rcnn_resnet101_coco 106 32 Boxes
Model name Speed (ms) Pascal mAP@0.5 (ms) Outputs
faster_rcnn_resnet101_kitti 79 87 Boxes

About

Object detection for autonomous car based on Mask-rcnn and coco dataset

License:MIT License


Languages

Language:Python 100.0%