BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition
来源：互联网 发布：上海程序员招聘 编辑：程序博客网 时间：2024/06/07 14:34
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：
0 0
- BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition
- 论文阅读(3)--SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-grained Recognition
- Fine-Grained Crowdsourcing for Fine-Grained Recognition(精读)
- SPDA-CNN:Unifying Semantic Part Detection and Abstraction for Fine-grained Recognition
- SPDA-CNN：Unifying Semantic Part Detectiojn and Abstraction for Fine-grained Recognition
- 论文阅读笔记 SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-grained Recognition
- Unsupervised Template Learning for Fine-Grained Object Recognition(精读)
- Unsupervised template learning for fine-grained object recognition
- Picking Deep Filter Responses for Fine-Grained Image Recognition
- 3D识别“3D Object Representations for Fine-Grained Categorization”
- 论文阅读(2)--Picking Deep Filter Responses for Fine-grained Image Recognition
- 噪声数据-The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
- 阅读小结：The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
- 细粒度图像识别文章 Picking Deep Filter Responses for Fine-grained Image Recognition 阅读笔记
- 论文阅读笔记 Picking Deep Filter Responses for Fine-grained Image Recognition
- 论文阅读：Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis
- 论文阅读(4)--Part-Stacked CNN for Fine-Grained Visual Categorization
- The Application of Two-level Attention Models in CNN for Fine-grained Image Classification
- 剑指Offer——算法复杂度中的O(logN)底数是多少
- android 艺术开发探索之动画（animation）
- tjut 3074
- tomcat中server.xml配置详解
- linux安装redis
- BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition
- jQuery和Prototype的兼容性和冲突的解决方法
- Spring源代码解析（十）：Spring Acegi框架授权的实现
- PHPCMS 模版嵌入PHP代码
- Spark SQL -- Catalyst
- eclipse历史版本下载
- 顺序锁(seqlock)
- 第一个jsp文档，hello world
- MySQL实例汇集
