Hon Hock Woon

Moving object extraction in PTZ camera using the integration of background subtraction and local histogram processing

This paper proposes a technique of extracting moving object using a pan-tilt-zoom (PTZ) camera. The technique is based on the integration of background subtraction and local histogram processing. Background images are modeled as multiple images and their corresponding camera pose information (pan and tilt angles). To detect object in current image, first the system will determine the most matched background based on the acquired PTZs pose information. Then the matched background is compensated with respect to current image, whereby the background subtraction is done between the two aligned images. The resultant output is then cleaned up using morphological opening operator, before local histogram processing is done and finally followed by closing operation. The results show the moving object can be successfully extracted after go through these four steps.

Non-standard Malaysian car license plate recognition

Automated car license plate recognition systems are developed and applied for purpose of facilitating the surveillance, law enforcement, access control and intelligent transportation monitoring with least human intervention. The challenging part of this system lies in accurately recognizing a non-standard plate that consists of various character fonts, character sizes, plate size, orientations, plate and character colors, materials, positions of numeric characters and alphabetic characters. The objective of the paper is to present our developed algorithms that cope with these practical variations in the context of non-standard Malaysian plate from image scene acquisition to optical character recognition. In each standard step of license plate recognition, we consider the processing of the plates under various environmental condition and non-standard formation of characters in real scene. The algorithm is tested with 500 Malaysian car plates in real-time and the result shown that the algorithm remains relatively robust under different conditions and car plate standard.

A New Multi-spectral Fusion Method for Degraded Video Text Frame Enhancement

Text detection and recognition in degraded video is complex and challenging due to lighting effect, sensor and motion blurring. This paper presents a new method that derives multi-spectral images from each input video frame by studying non-linear intensity values in Gray, R, G and B color spaces to increase the contrast of text pixels, which results in four respective multi-spectral images. Then we propose a multiple fusion criteria for the four multi-spectral images to enhance text information in degraded video frames. We propose median operation to obtain a single image from the results of the multiple fusion criteria, which we name fusion-1. We further apply k-means clustering on the fused images obtained by the multiple fusion criteria to classify text clusters, which results in binary images. Then we propose the same median operation to obtain a single image by fusing binary images, which we name fusion-2. We evaluate the enhanced images at fusion-1 and fusion-2 using quality measures, such as Mean Square Error, Peak Signal to Noise Ratio and Structural Symmetry. Furthermore, the enhanced images are validated through text detection and recognition accuracies in video frames to show the effectiveness of enhancement.

Video stabilization and tampering detection for surveillance systems using homography

Video stabilization is one of the key enhancements of video technology to compensate the variations in camera orientation and translation. In this paper, a method is proposed for surveillance systems to stabilize the camera vibrations and also to detect camera tampering. This method uses SURF feature detection and matching using RANSAC algorithm to achieve homogenous coordinates and then estimates the motion between consecutive frames. The motion is compensated in the region of interest using the calculated transformation matrix. The displacement of the region of interest in image sequence is also calculated to detect the attempts for camera tampering. The result shows the developed system has a promising performance in comparison with current methods in removing camera fluctuations from the input video and detecting camera tampering with high accuracy.

A new sharpness based approach for character segmentation in License plate images

Character segmentation from License plate is challenging as it suffers from non-uniform illumination, blur and touching adjacent character due to head light of vehicles effect etc. This paper presents a new approach based on sharpness of character and the space regions for segmentation. We explore Gradient Vector Flow Opposite Direction Pair of pixels for seed points selection. From the seed points, the proposed approach detects probable cuts between character components based on minimum cost path estimation. Then we propose a new sharpness for detecting candidate cuts from the probable cuts based on Laplacian zero crossing points and Sobel-Gradient. The average width of candidate cuts is considered as reference cut to identify the correct cuts between character components. Experimental results on real industry dataset of license plate shows that the proposed approach is robust to touching, blur, poor quality images. Further, comparative study with an existing approach shows that the proposed approach outperforms the existing approach.

An Automatic Robust Image Registration Algorithm for Aerial Mapping

Aerial mapping is attracting more attention due to the development in unmanned aerial vehicles (UAVs) and their availability and also vast applications that require a wide aerial photograph of a region in a specific time. The cross-modality as well as translation, rotation, scale change and illumination are the main challenges in aerial image registration. This paper concentrates on an algorithm for aerial image registration to overcome the aforementioned issues. The proposed method is able to sample automatically and align the sensed images to form the final map. The results are compared with satellite images that shows a reasonable performance with geometrically correct registration.

A pre-processing approach for efficient feature matching process in extreme illumination scenario

Video or image enhancement is a crucial part in image processing field as it improves the quality of the image before any further processes is applied on the image, which includes feature matching. In this paper, the accuracy of SURF feature descriptors used in feature matching between two input images of extreme illumination levels are evaluated. Based on the evaluation results, a novel pre-processing method to equalize both images intensity with respect to each other while maintaining the image content is proposed. We do so by fusing the cumulative histogram of the input images to compute a new cumulative histogram that will be used to remap both images. From this simple method, the results show that the intensity levels of the images are equalized and accuracy of the feature matching process is improved, in the event of extreme illumination scenario.

Kalman filter-based aggressive behaviour detection for indoor environment

The Automated video surveillance system is a very important modern tool, especially with the rising popularity of Internet of Things (IoT). The number of connected video cameras available for surveillance application keeps increasing, where even a low resolution mobile phone camera has been used to serve this purpose. For an enclosed room, one of the most important surveillance functions is to detect automatically aggressive behaviour, so that any verbal or physical fight can be stopped immediately. Moreover, an automated aggressive behaviour detection system is also suitable to be implemented in confinement room and prison, where an aggressive behaviour is more likely to occur. Aggressive behaviour can simply be defined as any behaviour that can potentially cause harm to the victim, either physically or mentally. Thus, this paper proposes a Kalman filter-based automated aggressive behaviour detection system by using average optical flow information. A filtered optical flow velocity by using background subtraction will be the input to Gaussian distribution to model the tracker observation. A bi-state tracker; normal and aggressive states will be tracked throughout the video, where the detection decision of each frame is dependent on either the smoothed normal state or smoothed aggressive state is bigger. Accuracy of the proposed system is moderate as the best performance is just 0.75, while the sensitivity performance is good with the highest value of 0.85. Hence, the system can be further improved by applying better decision module by embedding spatial information of the optical flow.

Elimination of character-resembling anomalies within a detected region using density-dependent reference point construction in an automated license plate recognition system

Abstract. The problem of eliminating character-resembling blobs on a detected region in the plate detection stage of an automated license plate recognition system is addressed. The proposed method amplifies the slight differences between the noncharacter blobs (anomalies) and the character blobs (true signal) to enhance the tractability. This method postulates on two propositions: (1) the anomalies are usually located around the true signal and the suspected anomalies and (2) blobs should be given less emphasis in computing a reference point. The first proposition is based on prior knowledge and observation; the second proposition is based on the fact that a reference point that takes anomalies into account is contaminated and thus misleading. The gist of the method mainly focuses on the methodology to emphasize the blobs differently in accordance to their location in computing the reference point that approximates the representative value of true signal properties more accurately, thus giving the effect of amplifying the slight differences. The performance of the method is evaluated on both its capability and consistency in solving certain types of anomalies.

Improved feature matching technique in low overlap area

Low overlap area is one of the problems in finding matching between two frames. When the camera moves on a static planar, the structure of the image deteriorates. As the camera moves, the same object might appear different with different camera views. Thus, it causes matching failure in subsequent images. We propose a rotation translation approach to assist existing feature matching algorithm. The method consists in rotating the image through a rotation translation model and applying Singular Value Decomposition (SVD) scheme and histogram patch similarity for filtering. The experimental results show that adding the proposed algorithm improves considerably the results in case of very small overlap region.