BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition
2016-08-17 15:38
1071 查看
CVPR 2016 本文没有开源代码
相关文档和代码 https://medusa.fit.vutbr.cz/traffic/research-topics/fine-grained-vehicle-recognition/unsupervised-processing-of-vehicle-appearance-for-automatic-understanding-in-traffic-surveillance/
本文使用 3D 矩形框相关信息作为 CNN 输入来提高车型识别
CNN 网络的输入图像是 unpacked version of the vehicles，辅助信息是 rasterized bounding boxes（车辆侧面，顶部，前部信息） 和 encoded viewpoints（车辆视角信息）
3.1. Unpacking the Vehicles’ Images
这是对车辆图像的一种归一化，将车的三个面：front/rear (F), side (S), and roof (R)提取出来，拼成一幅图像。
3.2. Viewpoint Encoding
车辆视角信息
3.3. Rasterized Bounding Boxes
4 BoxCars: New Dataset for Surveillance Vehicle Verification
每个模块对性能提升的量：
相关文档和代码 https://medusa.fit.vutbr.cz/traffic/research-topics/fine-grained-vehicle-recognition/unsupervised-processing-of-vehicle-appearance-for-automatic-understanding-in-traffic-surveillance/
本文使用 3D 矩形框相关信息作为 CNN 输入来提高车型识别
CNN 网络的输入图像是 unpacked version of the vehicles，辅助信息是 rasterized bounding boxes（车辆侧面，顶部，前部信息） 和 encoded viewpoints（车辆视角信息）
3.1. Unpacking the Vehicles’ Images
这是对车辆图像的一种归一化，将车的三个面：front/rear (F), side (S), and roof (R)提取出来，拼成一幅图像。
3.2. Viewpoint Encoding
车辆视角信息
3.3. Rasterized Bounding Boxes
4 BoxCars: New Dataset for Surveillance Vehicle Verification
每个模块对性能提升的量：
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- Bilinear CNN Models for Fine-grained Visual Recognition
- 论文笔记之： Bilinear CNN Models for Fine-grained Visual Recognition
- Unsupervised Template Learning for Fine-Grained Object Recognition(精读)
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- 论文提要“Part-based R-CNNs for Fine-grained Category Detection”
- Two-Stream RNN/CNN for Action Recognition in 3D Videos－阅读笔记
- 论文阅读(4)--Part-Stacked CNN for Fine-Grained Visual Categorization
- 细粒度图像识别文章 Picking Deep Filter Responses for Fine-grained Image Recognition 阅读笔记
- 论文阅读(2)--Picking Deep Filter Responses for Fine-grained Image Recognition
- Part-based R-CNNs for Fine-grained Category Detection(精读)
- The Application of Two-level Attention Models in CNN for Fine-grained Image Classification
- 论文阅读笔记 Picking Deep Filter Responses for Fine-grained Image Recognition
- Fine-tuning a Pretrained Network for Style Recognition
- 人群行为分类数据库--Novel Dataset for Fine-grained Abnormal Behavior Understanding in Crowd
- [行为识别] Two –Stream CNN for Action Recognition in Videos
- CS231n - CNN for Visual Recognition Assignment1 ---- SVM
- 论文阅读(3)--SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-grained Recognition
- 论文笔记：Segmentation as Selective Search for Object Recognition（ICCV2011）
- R-CNN学习笔记1：Selective Search for Object Recognition
- Undefined function 'conv2' for input arguments of type 'double' and attributes 'full 3d complex'.