车辆检测--A Closer Look at Faster R-CNN for Vehicle Detection
2017-12-28 09:28
627 查看
A Closer Look at Faster R-CNN for Vehicle Detection
Intelligent Vehicles Symposium , 2016 :124-129
本文主要分析了 Faster R-CNN 对于车辆检测这个问题的性能表现,尝试了各种训练尺寸和测试图像尺寸
Examples from the KITTI car dataset
The network structure of Faster R-CNN
训练数据集和测试数据集
数据集上车辆尺寸分布图
B. What training scale is appropriate?
我们之间用 Faster R-CNN 在 KITTI 数据集上训练测试,训练输入图像尺寸较长的一边为 1000像素, only achieving 64.02% on the moderate car examples while state of the art results reported on the KITTI website are 90.03%
这个差距如何解释了? 主要是降采样太多,车辆特征变小导致检测精度低
我们尝试了不同的训练图像尺寸
上图显示随着训练图像尺寸的增加,车辆检测精度是一直提升的。
However we used a training scale of 1500 for most of our analysis below for efficiency consideration.
C. Does the test scale matter?
测试图像的尺寸有没有影响了?
D. How many proposals are needed?
识别率上不去
11
Intelligent Vehicles Symposium , 2016 :124-129
本文主要分析了 Faster R-CNN 对于车辆检测这个问题的性能表现,尝试了各种训练尺寸和测试图像尺寸
Examples from the KITTI car dataset
The network structure of Faster R-CNN
训练数据集和测试数据集
数据集上车辆尺寸分布图
B. What training scale is appropriate?
我们之间用 Faster R-CNN 在 KITTI 数据集上训练测试,训练输入图像尺寸较长的一边为 1000像素, only achieving 64.02% on the moderate car examples while state of the art results reported on the KITTI website are 90.03%
这个差距如何解释了? 主要是降采样太多,车辆特征变小导致检测精度低
我们尝试了不同的训练图像尺寸
上图显示随着训练图像尺寸的增加,车辆检测精度是一直提升的。
However we used a training scale of 1500 for most of our analysis below for efficiency consideration.
C. Does the test scale matter?
测试图像的尺寸有没有影响了?
D. How many proposals are needed?
识别率上不去
11
相关文章推荐
- 小目标检测--A closer look: Small object detection in Faster R-CNN
- 行人检测 Is Faster R-CNN Doing Well for Pedestrian Detection?
- 行人检测 Is Faster R-CNN Doing Well for Pedestrian Detection?
- 人检测 Is Faster R-CNN Doing Well for Pedestrian Detection?
- 车辆检测“Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monoc”
- 嵌入式目标检测--Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection
- 人脸检测--Recurrent Scale Approximation for Object Detection in CNN
- 【深度学习:目标检测】RCNN学习笔记(1):Rich feature hierarchies for accurate object detection and semantic segmentat
- 【深度学习:目标检测】RCNN学习笔记(2):Rich feature hierarchies for accurate object detection and semantic segmentat
- 图像检测1-R-CNN-Rich featurehierarchies for accurate object detection and semantic segmentation
- 论文阅读之:Is Faster R-CNN Doing Well for Pedestrian Detection?
- Detection物体检测及分类方法总结(RFCN/SSD/RCNN/FastRCNN/FasterRCNN/SPPNet/DPM/OverFeat/YOLO)
- 【目标检测】Object Detection Faster RCNN算法解析
- CNN边缘检测--Richer Convolutional Features for Edge Detection
- Detection物体检测及分类方法总结(RFCN/SSD/RCNN/FastRCNN/FasterRCNN/SPPNet/DPM/OverFeat/YOLO)
- Face Detection with the Faster R-CNN (基于Faster RCNN的人脸检测)
- 车辆检测“Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model”
- 深度学习目标检测(object detection)系列(四) Faster R-CNN