Image Segmentation Using Thresholding and Swarm Intelligence

Ye, Zhiwei; Hu, Zhengbing; Lai, Xudong; Chen, Hongwei

doi:10.4304/jsw.7.5.1074-1082

Cited by 14 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus we can use the gray information of image to show the actual depth information. We usually get through the practical application scene to determine the camera construction height, and then estimate the distance between head and shoulder and the camera, the next step is to set gray threshold value [24]…”

Section: B Moving Objects Extraction Based On Distance Information Smentioning

confidence: 99%

Human Detection using HOG Features of Head and Shoulder Based on Depth Map

Qiu¹,

Zhou²,

Zhao³

et al. 2013

JSW

View full text Add to dashboard Cite

Conventional moving objects detection and tracking using visible light image was often affected by the change of moving objects, change of illumination conditions, interference of complex backgrounds, shaking of camera, shadow of moving objects and moving objects of self-occlusion or mutual-occlusion phenomenon. We propose a human detection method using HOG features of head and shoulder based on depth map and detecting moving objects in particular scene in this paper. In-depth study on Kinect to get depth map with foreground objects. Through the comprehensive analysis based on distance information of the moving objects segmentation extraction removal diagram of background information, by analyzing and comprehensively applying segmentation a method based on distance information to extract pedestrian’s Histograms of Oriented Gradients (HOG) features of head and shoulder[1], then make a comparison to the SVM classifier.

show abstract

Section: B Moving Objects Extraction Based On Distance Information Smentioning

confidence: 99%

Human Detection using HOG Features of Head and Shoulder Based on Depth Map

Qiu¹,

Zhou²,

Zhao³

et al. 2013

JSW

View full text Add to dashboard Cite

show abstract

“…In the work presented in [12], PSO, the Chaos Particle Swarm Optimization (CPSO) and artificial bees colony optimization (ABC) were used to find the optimal threshold of a 2-D histogram segmentation method. Experiments showed that the CPSO based approach has the best performance.…”

Section: Previous Workmentioning

confidence: 99%

“…Initialize a set of S agents with random positions in image space and random velocities For a number of iterations do {For each agent do {Assign each pixel to the nearest agent center & evaluate its fitness through eq (15) Evaluate its mass eq (10) and (11) Compute its acceleration eq (12) Update its velocity eq (13) Update its position eq (14) }} Show image partition based on pixels labeling to their nearest best centers…”

Section: The Gravitational Search Algorithm For Image Segmentationmentioning

confidence: 99%

Bio-Inspired Algorithms for Color Image Segmentation

Nebti¹

2013

IJCA

View full text Add to dashboard Cite

Effective image segmentation remains a challenging process as it constitutes a critical step to higher level image processing applications such as pattern recognition. In this paper, we present bio-inspired formulation to perform unsupervised image segmentation. Specifically, we used the Quantum PSO, the hybrid Gravitational PSO algorithm, a cooperative gravitational approach and the bees approach as powerful global classifiers to optimize the partition of image data into homogenous regions. The segmentation accuracy based on the bees' algorithm has the highest accuracy.

show abstract

“…In this step, it will detect and correct the skew LP to make location and verification accurately. In the second stage, LP characters and numbers are segmented [14], the LP characters and numbers are extracted, especially from the complex circumstance with various noise sources. Finally, and the recognition is carried out.…”

Section: Lpr Algorithmmentioning

confidence: 99%

Design of Intelligent Parking Management System Based on License Plate Recognition

Tian

Guo

Qiao

et al. 2014

JMM

View full text Add to dashboard Cite

Abstract-License Plate Recognition (LPR) which has been extensively studied recently is becoming one important part of Intelligent Transportation Systems (ITS). It is not only applied to public security monitoring, but also applied to a red light shot, speeding violation paparazzi, parking system and so on. The present paper introduces an intelligent parking management system based on LPR, recognizing license plate automatically at the parking lot access and realizing vehicle information integrated management conveniently. The software part is developed with VC++, QT and Microsoft Office Access Database. In the system, LPR is carried out through video streaming frame by frame to choose the best result with a high speed. After accurate LPR, the vehicle information, such as LP number, LP color, car type and access time, will be stored in system database. In addition, the system interface is designed very friendly and simple for administrators to operate, which can largely improve the whole performance of LPR system. Experimental results show that this parking management system can achieve high correct rate at 95%, and can be applied to real-time implementation.

show abstract

Image Segmentation Using Thresholding and Swarm Intelligence

Cited by 14 publications

References 12 publications

Human Detection using HOG Features of Head and Shoulder Based on Depth Map

Human Detection using HOG Features of Head and Shoulder Based on Depth Map

Bio-Inspired Algorithms for Color Image Segmentation

Design of Intelligent Parking Management System Based on License Plate Recognition

Contact Info

Product

Resources

About