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

@inproceedings{Zhao2017ARA,
  title={A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering},
  author={Xingding Zhao and Yueqing Wang and Yong Dou},
  year={2017}
}
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… 
3 Citations

Figures and Tables from this paper

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 and

Detection of Vehicle and Brake Light Based on Cascade and HSV Algorithm in Autonomous Vehicle

TLDR
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.

Detection of Vehicle and Brake Light Based on Cascade and HSV Algorithm in Autonomous Vehicle

  • Ebrahim Najafi Kajabad
  • Computer Science
    2018 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)
  • 2018
TLDR
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.

References

SHOWING 1-10 OF 12 REFERENCES

Non-maximum Suppression for Object Detection by Passing Messages Between Windows

TLDR
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.

Counting People in the Crowd Using a Generic Head Detector

TLDR
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.

SSD: Single Shot MultiBox Detector

TLDR
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.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

TLDR
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.

Efficient Non-Maximum Suppression

  • A. NeubeckL. Gool
  • Computer Science
    18th International Conference on Pattern Recognition (ICPR'06)
  • 2006
TLDR
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.

Mean shift analysis and applications

  • D. ComaniciuP. Meer
  • Mathematics
    Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
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.

Mean Shift Parallel Tracking on GPU

TLDR
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.

End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression

  • Li WanD. EigenR. Fergus
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
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.

Clustering by Passing Messages Between Data Points

TLDR
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.

ImageNet: A large-scale hierarchical image database

TLDR
A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.