Real-time object detection by a multi-feature fully convolutional network

  title={Real-time object detection by a multi-feature fully convolutional network},
  author={Y. Guo and Xiaoqiang Guo and Zhuqing Jiang and Aidong Men and Yun Zhou},
  journal={2017 IEEE International Conference on Image Processing (ICIP)},
Prior work on object detection depends on region proposals to guide the search for object instances. Generally, several thousand proposals must be processed, thus hurting the detection efficiency. In this paper, we propose a new model free from region proposals for object detection which treats detection task as a regression problem. To improve small-size object detection and localization, we employ the deep hierarchical features extracted from convolutional neural networks (CNNs). The… Expand


Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
  • 13,417
  • PDF
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
  • 23,303
  • Highly Influential
  • PDF
You Only Look Once: Unified, Real-Time Object Detection
  • 11,363
  • Highly Influential
  • PDF
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
  • 511
  • PDF
SSD: Single Shot MultiBox Detector
  • 10,642
  • PDF
Very Deep Convolutional Networks for Large-Scale Image Recognition
  • 47,433
  • Highly Influential
  • PDF
Object Detection with Discriminatively Trained Part Based Models
  • 8,747
  • PDF
Fast R-CNN
  • Ross B. Girshick
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
  • 10,762
  • Highly Influential
  • PDF
Going deeper with convolutions
  • 23,396
  • PDF
The Pascal Visual Object Classes (VOC) Challenge
  • 9,338
  • PDF