Haar Cascade Classifier and Lucas–Kanade Optical Flow Based Realtime Object Tracker with Custom Masking Technique

Mohiuddin, Karishma; Alam, Mirza Mohtashim; Das, Amit Kishor; Munna, Tahsir Ahmed; Allayear, Shaikh Muhammad; Ali, Md. Yousuf

doi:10.1007/978-3-030-03405-4_27

Cited by 2 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To begin with, the classifier model was first trained based on the item it was intended to identify (in this case, the goal was to track moving, unidentified aircraft in recorded footage). 5 As a result, the HAAR cascade classifier has to be properly trained before being used in this research. Using a laborious method, each frame from a sample video and a portion of a public database were prepared and collected to create the datasets.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…4 Further research is required in the field of tracing an item of interest by inferring its location from the movement of nearby items. 5 Beforehand, recently published research work was discussed below, which predominantly inspired the development of a solution in this research realm. 6 To begin, a fundamental tracking architecture has been used in Ref.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting and tracking the position of suspicious objects using vision system

Muthukrishnan,

Kannan,

Prabhu

et al. 2023

Artificial Intelligence for Security and Defence Applications

View full text Add to dashboard Cite

Vision-based object tracking is crucial for both civil and military applications. A range of hazards to cyber safety, vital infrastructure, and public privacy are posed by the rise of drones, or unmanned aerial vehicles (UAV). As a result, identifying suspicious drones/UAV is a serious issue that has attracted attention recently. The key focus of this research is to develop a unique virtual coloured marker based tracking algorithm to recognise and predict the pose of a detected object within the camera field-of-view. After detecting the object, proposed method begins by determining the area of detected object as reference-contour. Following that, a Virtual-Bounding Box (V-BB) is developed over the reference-contour by meeting the minimum area of contour criteria. In order to track and estimate the precise location of the detected object in two-dimensions during observations, a Virtual Dynamic Crossline with a Virtual Static Graph (VDC-VSG) was constructed to follow the motion of V-BB, which is considered as a virtual coloured marker. Additionally, the virtual coloured marker helps to avoid issues linked to ambient lighting and chromatic variation. To some extent, it can function efficiently during obstructions like rapid position fluctuations, low resolution and noises etc. The efficacy of the developed algorithm is evaluated by testing with significant number of aerial sequences, including benchmark footage and the outputs were outstanding, with better results. The suggested method will support future industry of computer vision-based intelligent systems. Potential applications of the proposed method includes object detection and analysis applied to the field of security and defence.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Detecting and tracking the position of suspicious objects using vision system

Muthukrishnan,

Kannan,

Prabhu

et al. 2023

Artificial Intelligence for Security and Defence Applications

View full text Add to dashboard Cite

show abstract

“…Figure 7c and Figure 7d show the detection results of the frame difference method [25] and the motion estimation and image matching method [26], respectively. We show the result from the scan line marking method [27] in Figure 7e results from the simple block-based sum of absolute differences flow (SD) method [28], and the Lucas-Kanade (LK) optical flow method [29] are given in Figure 7f,g. The weakness of the above three methods is that there are a few false positives, and both Figure 7c,e detected the sediment cloud in the background by mistake.…”

Section: Comparison With Six Target Detection Methodsmentioning

confidence: 99%

Detection of the Deep-Sea Plankton Community in Marine Ecosystem with Underwater Robotic Platform

Wang

Yang

Ding³

et al. 2021

Sensors

View full text Add to dashboard Cite

Variations in the quantity of plankton impact the entire marine ecosystem. It is of great significance to accurately assess the dynamic evolution of the plankton for monitoring the marine environment and global climate change. In this paper, a novel method is introduced for deep-sea plankton community detection in marine ecosystem using an underwater robotic platform. The videos were sampled at a distance of 1.5 m from the ocean floor, with a focal length of 1.5–2.5 m. The optical flow field is used to detect plankton community. We showed that for each of the moving plankton that do not overlap in space in two consecutive video frames, the time gradient of the spatial position of the plankton are opposite to each other in two consecutive optical flow fields. Further, the lateral and vertical gradients have the same value and orientation in two consecutive optical flow fields. Accordingly, moving plankton can be accurately detected under the complex dynamic background in the deep-sea environment. Experimental comparison with manual ground-truth fully validated the efficacy of the proposed methodology, which outperforms six state-of-the-art approaches.

show abstract

Haar Cascade Classifier and Lucas–Kanade Optical Flow Based Realtime Object Tracker with Custom Masking Technique

Cited by 2 publications

References 5 publications

Detecting and tracking the position of suspicious objects using vision system

Detecting and tracking the position of suspicious objects using vision system

Detection of the Deep-Sea Plankton Community in Marine Ecosystem with Underwater Robotic Platform

Contact Info

Product

Resources

About