Eng Thiam Lim

Adaptive mean and variance filter for detection of dim point-like targets

The problem of detecting small target in IR imagery has attracted much research effort over the past few decades. As opposed to early detection algorithms which detect targets spatially in each image and then apply tracking algorithm, more recent approaches have used multiple frames to incorporate temporal as well as spatial information. They often referred to as track before detect algorithms. This approach has shown promising results particularly for detection of dim point-like targets. However, the computationally complexity has prohibited practical usage for such algorithms. This paper presents an adaptive, recursive and computation efficient detection method. This detection algorithm updates parameters and detects occurrence of targets as new frame arrived without storing previous frames, thus achieved recursiveness. Besides, the target temporal intensity change is modeled by two Gaussian distribution with different mean and variance. The derivation of this generalized model has taken account of the wide variation of target speed, therefore detects wider range of targets.

Real-time Stereo Face Recognition by Fusing Appearance and Depth Fisherfaces

Reported 3D face recognition techniques assume the use of active 3D measurement for 3D facial capture. However, active method employ structured illumination (structure projection, phase shift, gray-code demodulation, etc) or laser scanning, which is not desirable in many applications. A major problem of using passive stereo is its lower 3D face resolution and thus no passive method for 3D face recognition has been reported. In this paper, a real-time passive stereo face recognition system is presented. Entire face detection, tracking, pose estimation and face recognition are investigated. We used SRI Stereo engine that outputs sub-pixel disparity automatically. An investigation is carried out in combining 3D and 2D information for face recognition. The straightforward two-stage principal component analysis plus linear discriminant analysis is carried out in appearance and depth face images respectively. A probe face is identified using sum of the weighted appearance and depth linear discriminant distances. We investigate the complete range of linear combinations to reveal the interplay between these two paradigms. The improvement of the face recognition rate using this combination is verified. The recognition rate by the combination is higher than that of either appearance alone or depth alone. We then discuss the implementation of the algorithm on a stereo vision system. A hybrid face and facial features detection/tracking approach is proposed which collects near-frontal views for face recognition. Our face detection/tracking approach automatically initializes without user intervention and can be re-initialized automatically if the tracking of the 3D face pose is lost. The experiments include two parts. Firstly, the performance of the proposed algorithm is verified on XM2VTS database; Secondly, the algorithm is demonstrated on a real-time stereo vision system. It is able to detect, track and recognize a person while walking toward a stereo camera.

Face tracking and recognition from stereo sequence

In this paper, we present a face recognition system that is able to detect, track and recognize a person walking toward a stereo camera. Integrating stereo and intensity pairs, pose can be detected and tracked. Face images, which are suitable for recognition, from stereo sequence can be selected automatically based on the pose. Then the straightforward Fisherface is carried out on the selected face images. Results of the tracking and recognition depict that this video based stereo approach provides a more robust performance since the 3D information is considered.

Dim point target detection in IR imagery using multistage IIR filter

Temporal profiles of point-like dim targets and the extended cloud pixels provide useful information in detecting the target. Among the recent methods that utilize temporal profile of pixel in detecting point target are Triple Temporal Filter (TTF) and Continuous Wavelet Transform (CWT). TTF uses two damped sinusoidal filters, an exponential averaging filter with six appropriate coefficients to deal with different aspects of clutter. TTF is recursive and efficient in detecting point targets without applying any threshold techniques. The performance of CWT is comparable to TTF but all the frames in a sequence need to be stored. Therefore it is computationally complex algorithm.

Multimode fusion algorithm for robust dim point-like target detection

This paper presents a multi-mode fusion algorithm for detection and tracking of dim, point-like target. The key contribution of this paper includes the effective fusion approach to harvest the advantages and complement the disadvantages of various algorithms using conditional voting. From qualitative analysis, these algorithms are separated into two classes, i.e. main and supporting algorithms. In the multi-mode fusion algorithm high confidence is placed on the main algorithms with supporting algorithms used to further reduce the false alarm. The main algorithms trigger a voting process and detection is confirmed true if any of the supporting algorithms report detection. The multi-modal fusion algorithm has lower false alarm and moderate true detection rate compared to any individual algorithm namely, Triple Temporal Filter, Frame Differencing, Continuous Wavelet Transform, Max-median and 2-D Mexican hat filter. Besides, a novel variability filter is proposed to remove strong glint thus reduces false alarm. Kalman filter is used to track the detected targets. A novel track decision algorithm to continue or terminate the track when target disappears is proposed. Prior knowledge of target in Kalman filter is fed forward to an Adaptive 3-D Matched filter to improve the performance. Three sets of real-world infrared image sequences with very different background and target characteristics were used to test the robustness of the multi-modal fusion algorithm. The algorithm performs satisfactorily in all the image sequences. Video clips will also be presented.

Detection of small targets in IR image sequences using VSLMS

A Vertical-Strip Least Mean Squared (VSLMS) algorithm is proposed to enhance the detection of small moving targets in IR image sequences. This algorithm is an improvement over the Two-Dimensional LMS (TDLMS), which is designed to detect small targets within highly correlated background of static images. This paper focuses on processing IR image sequences with different background features with layers of sky, sea and land clutter. The VSLMS uses multiple LMS modules and a different scanning method to process individual lines in the IR image sequences. Simulation results show successful enhancement of very small targets in an IR mage sequence.

Tracking of low-observable small targets against clutter

Detection and tracking of low-observable moving targets against heavy clutter in a sequence of infrared images is an important research area. The focus of research in this area is to reliably pick up the most potential targets, track the targets with varying speed and direction, and at the same time reduce the false alarm rate to an acceptable level. However, there is no single method that works equally well in all situations. This paper presents an integrated algorithm based on area-correlation tracker (ACT) and Kalman filter for improving ACT performance for targets with varying speed and direction. Divergence and loss of target when the target is stationary are the two typical problems associated with ACT. In our algorithm, we propose to overcome these shortcomings by introducing an online procedure for updating (or not updating in the case of occlusions) the reference template, in conjunction with linear predictions by using a Kalman filter.

Wearable high-tech gear for homeland security personnel

Recent homeland security problems in various countries indicate that fixed surveillance systems at important places are not adequate enough. As the security threats take new dimensions in future, mobile smart security personnel wearing high-tech gear will form the basic infrastructure. See first, listen first, detect first, track first, communicate first with peers, assess the threat and coordinate with security head-quarters are the functions of high-tech gear. This paper proposes a high-tech gear involving (i) hands-free and obtrusion-free textile-based wearable microphone array to capture users voice and interface with body-worn computer, (ii) microphone arrays embedded in textiles to listen and record others voices from a distance, (iii) miniature cameras embedded in the shirt to provide the user with omni vision (iv) wireless personal display as GUI hidden in textile or natural glasses, (v) GPS and body area network for positional awareness for information in the form of text or textile integrated, (vi) reconfigurable HW/SW for all the above functions configured in the form of a usual belt. The main focus of this paper is how to configure the high-tech gear with all these sophisticated functions to disappear into the natural wearables of the user giving him normal look in the public. This project is sponsored by Defence Science & Technology Agency, Ministry of Defence, Singapore. This paper covers multi-discipline technologies at system level, hence not possible to go into details of any subsystem. The main objective of this paper is to share our thoughts and get feedback. Progress and some critical design issues are discussed in this paper.

Dim point target detection and tracking system in IR imagery

Temporal profiles of point-like dim targets and the extended cloud pixels provide useful information in detecting the targets. Among the recent methods that utilize temporal profile of pixel in detecting point target are Triple Temporal Filter (TTF) and Continuous Wavelet Transform (CWT). TTF uses two damped sinusoidal filters, an exponential averaging filter with six appropriate coefficients to deal with different aspects of clutter. TTF is recursive and efficient in detecting point targets without applying any threshold techniques. The performance of CWT is comparable to TTF but all the frames in a sequence need to be stored. Therefore it is computationally complex algorithm.