Robust single object tracker based on kernelled patch of a fixed RGB camera

Zulkifley, Mohd Asyraf

doi:10.1016/j.ijleo.2015.10.130

Cited by 8 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, an improvment in the detection algorithm will lead to better tracking accuracy accordingly. Among others, some good trackingby-detection algorithms are presented in [14][15][16][17][18][19][20]. Some of these tracking approaches are able to function wellunder good lighting conditions, however, their performance deteriorate as the environment becomes darker such as in night surveillance application.…”

Section: Related Workmentioning

confidence: 99%

Deep-learning based single object tracker for night surveillance

Kadim¹,

Zulkifley²,

Hamzah³

2020

IJECE

Self Cite

View full text Add to dashboard Cite

Tracking an object in night surveillance video is a challenging task as the quality of the captured image is normally poor with low brightness and contrast. The task becomes harder for a small object as fewer features are apparent. Traditional approach is based on improving the image quality before tracking is performed. In this paper, a single object tracking algorithm based on deep-learning approach is proposed to exploit its outstanding capability of modelling object’s appearance even during night. The algorithm uses pre-trained convolutional neural networks coupled with fully connected layers, which are trained online during the tracking so that it is able to cater for appearance changes as the object moves around. Various learning hyperparameters for the optimization function, learning rate and ratio of training samples are tested to find optimal setup for tracking in night scenarios. Fourteen night surveillance videos are collected for validation purpose, which are captured from three viewing angles. The results show that the best accuracy is obtained by using Adam optimizer with learning rate of 0.00075 and sampling ratio of 2:1 for positive and negative training data. This algorithm is suitable to be implemented in higher level surveillance applications such as abnormal behavioral recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep-learning based single object tracker for night surveillance

Kadim¹,

Zulkifley²,

Hamzah³

2020

IJECE

Self Cite

View full text Add to dashboard Cite

show abstract

“…The section would then go to discuss CNN and its applications in tracking systems. The majority of the previous studies have investigated the use of single cameras for object tracking [1][2][3][4][5][6].…”

Section: Related Workmentioning

confidence: 99%

“…The study reported in [iterature [5] makes use of a Probability Hypothesis Density (PHD) filter to track the visual features which belong to a vehicle detected via a single camera. In another study [6], combination of a kernel-based histogram and a feature detector approach is proposed for the purpose of object tracking. The study employs two color spaces, i.e., RGB and HSI, and the kernel method to improve histogram accumulation.…”

Section: Related Workmentioning

confidence: 99%

“…Once the object is detected and represented, its position is located in each of the new frames. The majority of the previous studies on object tracking have investigated surveillance systems with single cameras [1][2][3][4][5][6] using color information. However, in single-camera systems, the two factors of variable lighting conditions and occlusion would cause imperfect tracking results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Gating Network for Object Tracking

Feizi

2019

IJE

View full text Add to dashboard Cite

A B S T R A C TObject tracking through multiple cameras is a popular research topic in security and surveillance systems especially when human objects are the target. However, occlusion is one of the challenging problems for the tracking process. T his paper proposes a multiple-camera-based cooperative tracking method to overcome the occlusion problem. The paper presents a new model for combining convolutional neural networks (CNNs), which allows the proposed method to learn the features with high discriminative power and geometrical independence. In the training phase, the CNNs are first pre-trained in each of the camera views, and a convolutional gating network (CGN) is simultaneously pre-trained to produce a weight for each CNN output. The CNNs are then transferred to the tracking task where the pre-trained parameters of the CNNs are re-trained by using the data from the tracking phase. T he weights obtained from the CGN are used in order to fuse the features learnt by the CNNs and the resulting weighted combination of the features is employed to represent the objects. Finally, the p article filter is used in order to track objects. The experimental results showed the efficiency of the proposed method in this paper.

show abstract