A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering

  title={A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering},
  author={Xin Zhao and Yueqing Wang and Yong Dou},
Non-maximum suppression is an important step in many object detection and object counting algorithms. In contrast with the extensive studies of object detection, NMS method has not caused too much attention. Although traditional NMS method has demonstrated promising performance in detection tasks, we observe that it is a hard decision approach, which only uses the confidential scores and Intersection-over-Unions (IoUs) to discard proposals. By this way, NMS method would keep many false… Expand
3 Citations
Distance-Based Method used to Localize the Eyeball Effectively for Cerebral Palsy Rehabilitation
Iris plays a vital role in human life for object identification. Many models and techniques were proposed and suggested for detecting the Iris, but the accuracy was not achieved up to the level andExpand
Detection of Vehicle and Brake Light Based on Cascade and HSV Algorithm in Autonomous Vehicle
A method of image processing to tracking vehicle and brake light which includes the cascade classifier algorithm based on the classification of a collection of information which can be useful for mobile robots and industrial robots in terms of object detection and recognition in real time. Expand
Detection of Vehicle and Brake Light Based on Cascade and HSV Algorithm in Autonomous Vehicle
  • Ebrahim Najafi Kajabad
  • 2018 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)
  • 2018
Autonomous vehicles make the main part of the intelligent transportation system. In addition, the accident statistics illustrates that the number of accidents accrued in the night, bad weatherExpand


Non-maximum Suppression for Object Detection by Passing Messages Between Windows
This paper builds on the recent Affinity Propagation Clustering algorithm, which passes messages between data points to identify cluster exemplars and shows that it provides a promising solution to the shortcomings of the greedy NMS. Expand
A Convnet for Non-maximum Suppression
This work proposes a convnet designed to perform non-maximum suppression of a given set of detections, and overcomes the intrinsic limitations of greedy NMS, obtaining better recall and precision. Expand
Counting People in the Crowd Using a Generic Head Detector
This paper detects the head region since this is the most visible part of the body in a crowded scene and proposes a novel interest point detector based on gradient orientation feature to locate regions similar to the top of head region from gray level images. Expand
SSD: Single Shot MultiBox Detector
The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
Efficient Non-Maximum Suppression
  • A. Neubeck, L. Gool
  • Computer Science
  • 18th International Conference on Pattern Recognition (ICPR'06)
  • 2006
This work scrutinize a low level computer vision task - non-maximum suppression (NMS) - and derive several algorithms ranging from easy-to-implement to highly-efficient. Expand
Mean shift analysis and applications
  • D. Comaniciu, P. Meer
  • Mathematics, Computer Science
  • Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
A nonparametric estimator of density gradient, the mean shift, is employed in the joint, spatial-range (value) domain of gray level and color images for discontinuity preserving filtering and image segmentation and its convergence on lattices is proven. Expand
Mean Shift Parallel Tracking on GPU
Experiments on public available CAVIAR videos show that the proposed parallel tracking algorithm achieves large speedup and has comparable tracking performance, compared with the traditional serial MS tracking algorithm. Expand
End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression
  • Li Wan, D. Eigen, R. Fergus
  • Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
This work trains a new model using a new structured loss function that considers all bounding boxes within an image, rather than isolated object instances, and enables the non-maximal suppression operation, previously treated as a separate post-processing stage, to be integrated into the model. Expand
Clustering by Passing Messages Between Data Points
A method called “affinity propagation,” which takes as input measures of similarity between pairs of data points, which found clusters with much lower error than other methods, and it did so in less than one-hundredth the amount of time. Expand