Logo image
Tracking by Detection with Convolution Sharing: A Deep Multi-vehicle Tracking System
Thesis

Tracking by Detection with Convolution Sharing: A Deep Multi-vehicle Tracking System

He, Liang
Masters, 國立清華大學, 資訊系統與應用研究所
2015

Abstract

追蹤 深層學習 卷積神經網路 車輛 偵測 tracking deep learning CNNs vehicle detection
This thesis presents a novel system for high performance multi-vehicle tracking. The main concept of our system is tracking by detection, or to say, detection based tracking. We consider the whole tracking problem as a combination of per-frame object detection, detection result regression, embedding metric of detection result, and association of final detection result. The core technique in implementation is convolution sharing. We share the same rich features between convolutional neural network (CNN) models that are designed for different parts of our system. By integrating the concept and the core technique mentioned above, with a properly scheduled training process for specific CNN models, our system achieves a good performance when evaluating on the object tracking datasets of KITTI, a challenging real-world computer vision benchmark suite. Moreover, even though our tracking system is built on multi-stage and multi-CNN models, it can run efficiently in nearly real time.

Metrics

1 Record Views

Details

Logo image