Multiple Target Detection Using Optical Flow

Viswanath, H.C.; Jones, Richard

doi:10.1109/icsmc.1988.712860

Cited by 2 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detecting target motion is equivalent to detecting the anomalous optical flow [22]. In this technique, the light flow method takes the performance movement of the gray scale mode in the image as the light flow, and the speed of the physical point can be described by 3D positioning and projected on the plane to form the corresponding image.…”

Section: Optical Flow Methodsmentioning

confidence: 99%

Research on the Robot’s Intelligent Inspection, Its Target Detection Method

Lu¹,

Badarch²

2022

AJCST

View full text Add to dashboard Cite

Intelligent inspection robot has the characteristics of programmable, and can be applied to various inspection environments. In general, studies show the present trend is to replace humans with an inspection robot thereby reducing the risks and improving the inspection efficiency. The intelligent inspection robot is based on intelligent technology and has programmability. In this paper, based on the research of intelligent inspection robot technology, we analyze inspection techniques, their algorithms, functions, characteristics and other important parameters. The research mainly focuses on two things: the target detection, methods and improved Adaboost algorithm to improve the accuracy of target detection; the Camshift algorithm which is improved to complete tracking design, timely data acquisition, timely problem discovery and timely solution. The target detection and target tracking are studied and their algorithms are analyzed. We present that a tracking algorithm based on improved Camshift deals with the problems which exist in traditional Camshift algorithm. In addition, we present Meanshift algorithm improves the Camshift algorithm for the whole-process tracking, automation and intelligence level, and efficient tracking. Next, combined with relevant technologies and techniques, the algorithm is improved to complete the target detection design and tracking design, and to solve the problems of inaccurate target detection and untimely detection.

show abstract

Section: Optical Flow Methodsmentioning

confidence: 99%

Research on the Robot’s Intelligent Inspection, Its Target Detection Method

Lu¹,

Badarch²

2022

AJCST

View full text Add to dashboard Cite

show abstract

Multitarget detection using Kalman-based average displacement estimator

Viswanath¹,

Jones

1993

IEEE Trans. Aerosp. Electron. Syst.

Self Cite

View full text Add to dashboard Cite

The anomaly in the displacement estimates obtained from a low-level Kalman-based average displacement estimator is used to detect multiple targets (obtain returns) in a forward-looking infrared (FLIR) scene. In future, the displacement estimates originating from the targets could be associated with the returns (detected multiple targets of this work), and hence obtain an updated estimated position of the targel. This procedure could be repeated for all targets in the scene to obtain multitarget tracking. The behavior of the expected value of the displacement estimates as a function of the number of iterations is investigated. Also, the behavior of the displacement error covariance matrix and the Kalman gain matrix are investigated as a function of the number of iterations.

show abstract

Multiple Target Detection Using Optical Flow

Cited by 2 publications

References 3 publications

Research on the Robot’s Intelligent Inspection, Its Target Detection Method

Research on the Robot’s Intelligent Inspection, Its Target Detection Method

Multitarget detection using Kalman-based average displacement estimator

Contact Info

Product

Resources

About