Moving object tracking method based on improved lucas-kanade sparse optical flow algorithm

Li, Dan; Jiang, Daihong; Bao, Rong; Sun, Jinping; Wen-Jing, Zhao; Wang, Chao

doi:10.1109/isc2.2017.8090850

Cited by 15 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It makes three assumptions viz., brightness constancy (the same keypoint appearing in both images should look similar), limited motion (keypoints do move very far), and spatial coherence (keypoints move within a small neighborhood) [43]. This method has been shown to be well suited for object tracking [15], and our experiments show that it is also energy-efficient (see Fig. 6 of §5.2).…”

Section: Real-time Object Trackermentioning

confidence: 81%

Frugal following

Apicharttrisorn

Ran

Chen

et al. 2019

Proceedings of the 17th Conference on Embedded Networked Sensor Systems

View full text Add to dashboard Cite

Accurate tracking of objects in the real world is highly desirable in Augmented Reality (AR) to aid proper placement of virtual objects in a user's view. Deep neural networks (DNNs) yield high precision in detecting and tracking objects, but they are energy-heavy and can thus be prohibitive for deployment on mobile devices. Towards reducing energy drain while maintaining good object tracking precision, we develop a novel software framework called MARLIN. MAR-LIN only uses a DNN as needed, to detect new objects or recapture objects that significantly change in appearance. It employs lightweight methods in between DNN executions to track the detected objects with high fidelity. We experiment with several baseline DNN models optimized for mobile devices, and via both offline and live object tracking experiments on two different Android phones (one utilizing a mobile GPU), we show that MARLIN compares favorably in terms of accuracy while saving energy significantly. Specifically, we show that MARLIN reduces the energy consumption by up to 73.3% (compared to an approach that executes the best baseline DNN continuously), and improves accuracy by up to 19× (compared to an approach that infrequently executes the same best baseline DNN). Moreover, while in 75% or more cases, MARLIN incurs at most a 7.36% reduction in location accuracy (using the common IOU metric), in more than 46% of the cases, MARLIN even improves the IOU compared to the continuous, best DNN approach. CCS CONCEPTS • Human-centered computing → Ubiquitous and mobile computing systems and tools.

show abstract

Section: Real-time Object Trackermentioning

confidence: 81%

Frugal following

Apicharttrisorn

Ran

Chen

et al. 2019

Proceedings of the 17th Conference on Embedded Networked Sensor Systems

View full text Add to dashboard Cite

show abstract

“…For the purpose of detecting and subtracting background, the clustering based methods such as sequential clustering [8], and codebook [9] have been applied. As for deep learning methods, optical flow [18] plays an important part in solving motion detection with a static background [19] [20]. Optical flow tracks the moving object locations between two frames and separates the moving objects from the static background.…”

Section: Related Workmentioning

confidence: 99%

Motion detection in a color video sequence with an application to monitoring a baby

Yan¹,

Guo²,

He³

et al. 2022

View full text Add to dashboard Cite

Personal real-time video monitoring devices are popular in recent years especially for people living in bigger houses who are taking care of babies. People take advantage of a real-time video monitoring device to monitor the babies' activities while they are occupied by other issues. However, danger happens any time in any situations. It is necessary for a baby monitoring device to have a motion detection function to trigger recording functions or alert the guardians. This paper introduces a solution for the motion detection problem. The solution combines statistical methods, kernel density estimation and histogram analysis methods, and deep learning method for detecting the salient object. The final outputs are both the motion levels indicating the severity of the motions and the bounding boxes indicating the location of the motion happening in the video frame. The different levels of motion can later be used as triggers for different functions built into the device, such as starting video recording, playing sirens, etc., and the bounding boxes can provide reference focus areas for the guardians to check the details of the motion to decide whether to take actions or not.

show abstract

“…Algoritma yang digunakan pada umumnya adalah optical flow, background substraction, template matching, camshift, meanshift, dan filter Kalman. Optical flow dapat melakukan pelacakan dengan stabil tetapi akan terjadi galat yang cukup besar jika objek terhalang sesaat [4], [5]. Algoritma template matching memiliki karakteristik yang berkebalikan dengan algoritma optical flow, yaitu dapat melakukan pelacakan meskipun objek terhalang sesaat tetapi kurang stabil [4], [6], [7].…”

Section: Pendahuluanunclassified

“…Hasil penelitian [5]- [10] menjelaskan keandalan sistem pelacakan yang dibangun, dimana sistem dapat melakukan deteksi dan pelacakan objek yang bergerak cepat dan terhalang sesaat. Namun, penelitian-penelitian tersebut tidak menjelaskan tentang kecepatan komputasi dan besar nilai galat jarak koordinat yang dihasilkan.…”

Section: Hasil Dan Pembahasanunclassified

Sistem Pelacakan Objek Menggunakan Kombinasi Algoritma Optical Flow dan Template Matching

Fahriannur

Mardiyanto

Siswanto

2018

Jurnal Teknologi dan Sistem Komputer

View full text Add to dashboard Cite

-This study is aimed to develop a tracking system algorithm by combining optical flow and template matching algorithms to strengthen tracking and minimize the resulting errors. The system has been tested on a football video game with the ball as a tracking object. The optical flow and template matching algorithms are used interchangeably based on the coordinates of both ranges calculated using the Euclidean distance equation. The result shows that the system is able to do tracking, although it is temporarily blocked by other objects, more stable and the distance error between the coordinates of the tracking result and the actual coordinates is not more than 110 pixels compared to using only optical flow or template matching algorithm. [9] mengembangkan sistem pelacakan video menggunakan algoritma frame differencing. Deteksi objek dilakukan dengan cara frame sekarang dikurangi dengan frame sebelumnya dan di antara objek yang terdeteksi dipilih salah satu objek menggunakan template matching. Hal ini mempercepat proses komputasinya dibandingkan dengan hanya menggunakan template matching saja. Parrila dkk. Keywords[10] membangun sistem pelacakan pada video lalu lintas jalan raya dengan menggunakan algoritma optical flow yang handal, yaitu dapat terus *) Penulis korespondensi (Meilana Siswanto)

show abstract

Moving object tracking method based on improved lucas-kanade sparse optical flow algorithm

Cited by 15 publications

References 9 publications

Frugal following

Frugal following

Motion detection in a color video sequence with an application to monitoring a baby

Sistem Pelacakan Objek Menggunakan Kombinasi Algoritma Optical Flow dan Template Matching

Contact Info

Product

Resources

About