• Monocular Visual Object 3D Localization in Road Scenes

    (15 Jul 2019)
    3D localization of objects in road scenes is important for autonomous driving and advanced driver-assistance systems (ADAS). However, with common monocular camera setups, 3D information is difficult to obtain. In this paper, we propose a novel and robust method for 3D localization of monocular visual objects in road scenes by joint integration of depth estimation, ground plane estimation, and multi-object tracking techniques.
  • Object Detection on KITTI dataset using YOLO and Faster R-CNN

    (20 Dec 2018)
    This post is going to describe object detection on KITTI dataset using three different detectors, YOLOv2, YOLOv3, Faster R-CNN and compare their performance evaluated by uploading the results to KITTI evaluation server.
  • Train YOLOv2 with KITTI dataset

    (29 Jul 2018)
    KITTI dataset contains many real-world computer vision benchmarks for autonomous driving. There are many tasks including stereo, optical flow, visual odometry, 3D object detection and 3D tracking. YOLOv2 is a popular technique for real-time object detection. There are many pre-trained weights for many current image datasets. However, YOLOv2 doesn't perform well on KITTI object dataset.