陈志波  (教授)

博士生导师

电子邮箱:

学位:博士

毕业院校:Tsinghua University

   

Multi-view Vehicle Type Recognition with Feedback-enhancement Multi-branch CNNs

点击次数:

Abstract

Vehicle type recognition (VTR) is a quite common requirement and one of key challenges in real surveillance scenarios such as intelligent traffic and unmanned driving. Usually coarse-grained VTR and fine-grained VTR are applied in different applications, and the challenge from multiple viewpoints is critical for both cases. In this paper, we propose a Feedback- enhancement Multi-branch CNN (FM-CNN) to solve the chal- lenge in these two cases. The proposed FM-CNN takes three derivatives of an image as input and leverages the advantages of hierarchical details, feedback enhancement, model average and stronger robustness to translation and mirroring. A single global cross-entropy loss is insufficient to train such a complex CNN and so we add extra branch losses to enhance feedbacks of each branch. Though reusing pre-trained parameters, we propose a novel parameter update method to adapt FM-CNN to task-specific local visual patterns and global information in new datasets. To test the effectiveness of FM-CNN, we create our own Multi-view VTR (MVVTR) dataset since there is no such datasets available. And for fine-grained VTR, we use CompCars dataset. Compared with state-of-the-art solutions, the proposed FM-CNN demonstrates better performance in both coarse-grained and fine- grained scenarios. For coarse-grained VTR, it achieves 94.9% Top-1 accuracy on MVVTR dataset. For fine-grained VTR, it achieves 91.0% Top-1 and 97.8% Top-5 accuracies on CompCars dataset.

Paper

to be published.

Get Database

You can download the publicly available release of the source code by clicking THIS link. Please fill THIS FORM and the password will be sent to you.

Get Source Code

You can download the publicly available release of the source code by clicking THIS link. Please fill THIS FORM and the password will be sent to you.


上一条: Dataset Publication for “ImmerTai: Immersive Taichi Motion Learning in Various VR Environments”

下一条: IMCL 3D-HEVC Stereo Video Quality Database - Phase I