Wong Poh Lee

Tracking Multiple Fish in a Single Tank Using an Improved Particle Filter

Studies on tracking fishes have become a popular research endeavour in recent years. Many methods have been used to track fishes by integrating microchips in fishes, using infra-red cameras, image processing and motion sensor. The use of particle filter in the process of tracking has been widely used by researchers. Particle filters is used to track people, fluid movement and animals. In this paper, the particle filter algorithm is improved to track multiple fish in a fish tank. The aim is to identify every fish trajectories and fish target location for further analysis. The main challenge is to ensure that the correct fish are tracked and the algorithm manages to identify specific fish even if they overlaps with each another. The objective of the study is to improve the existing particle filter to track multiple fish in a single fish tank. The improved algorithm contains an additional cache which stores the object’s position to estimate the next potential move of the fish. The result is evaluated by comparing existing algorithm without the enhancement with the improved algorithm. Besides, suggestions in improving the particle filter will also be discussed in this paper.

Recognition of fish based on generalized color Fourier descriptor

Recognizing objects using computational methods have become a popular research endeavor among researchers. In this paper, the recognition of fish based on GCFD (Generalized Color Fourier Descriptor) is introduced. The features are extracted using the GCFD technique which represents the image in a frequency domain. By analyzing the frequencies, the non-related information (backgrounds, not required lines or borders) are identified by performing some spectrum changes on the frequencies. The required objects in this study are the fish. In other words, the frequencies corresponding to the fish are maintained while other frequencies are removed from the frequency domain. After removing the non-related frequencies, the frequency domain is inversed in order to obtain the required image for further image processing. GCFD is used as a descriptor to extract the features of the fish as it is invariant to rotation and translation. A cultured fish tank installed with high-end video cameras is required to record the video from side and top views. Koi fish are chosen due to their active swimming behavior, variety of colors and easy-to-adapt habitat in the water. The evaluation of the technique is based on Bhattacharyya Distance. Some improvements were obtained in the recognition rate using the GCFD compared with existing color descriptors. The improvement can lead to better classifications of objects.

Tracking Multiple Fishes Using Colour Changes Identification and Enhanced Object Tracking Algorithm

Tracking multiple fishes using computational methods have become a research endeavor among researchers. Different concepts have been taken such as installing water sensors and video cameras to identify movement speed, colours, shapes and swimming patterns displayed by the fishes. In this research, an enhanced algorithm consisting of motion detection algorithm and condensation algorithm is proposed. This algorithm is further integrated with colour changes identification technique which considers the changes in colour on fishes. This is to identify overlapping fishes and to detect the distance between the camera and the fishes in the water. In our case study, a cultured fish tank installed with water sensors to monitor water pH, dissolved oxygen and temperature is set up together with two network cameras. Koi fishes are chosen due to their active swimming behaviour, variety of colours and easy-to-adapt habitat in the water. A real-time prototype system which models the fish swimming pattern consisting of the enhanced algorithm and the colour changes identification is developed.

Enhanced Object Tracking in Real-Time Environment Using Dual Camera

Research in object tracking has become a popular research domain among researchers. The use of video cameras to capture motion images instead of static images poses a great challenge to researchers in terms of speed and accuracy of the object tracking and detection. In this paper, fish are used in the experiment due to its active swimming behaviour which emulates the movement of many living objects such as humans or animals. The main problem faced in the tracking process is that the fishes swim in various directions and angles. It is difficult to track and identify a specific fish in a school of fish in most cases. Besides, the fish may also appear to be overlapping one another. There exists several object tracking systems in the market but the focuses are mainly on surveillance. Besides, there is still room for improvement in the tracking process. Therefore, this paper focuses on using an additional camera for tracking fish in real-time environment. The evaluation of the tracking process consists of using the same video with an additional camera positioned above the fish tank. Results show improvement when an additional camera is used to obtain additional information mainly the trajectory patterns of the fish which contributes to bringing a higher accuracy of the tracking system.

Development of WILMS: Well Inform Landslide Monitoring System for USM Healthy Campus

Slope monitoring system was installed for the purpose of monitoring the hill development for student accommodation which houses three main blocks of hostels. This was implemented under a special programme known as Healthy Campus which covers all aspects conducive to student, staff and environment. A full package of pilot study has been conducted by a group of experts in the field to run a monitoring and mitigation system for Universiti Sains Malaysia (USM) hostels. WILMS (Well-Inform Landslides Monitoring System) is a real-time web monitoring system which integrates the use of SMS (Short Messaging Services) and MMS (Multimedia Messaging Services) technology to inform and to alert users of different needs about the presence of a pessimistic change in land stability. The uniqueness of this application is that it makes monitoring job easier, without needing constant human power while maintaining accurate data acquisition cocpyntinuously and reducing human errors. This method is offering cheaper solution as well as sustaining environmental issues.

Design of Embedded System for Grid Handtop Computing (ESGHC)

This paper discusses the design of the embedded system for grid handtop computing (ESGHC), the implementation and the methods used in ESGHC. ESGHC applies the grid computing technology which is built under a grid environment for handtop devices. By having ESGHC, sharing of handtop devices in terms of computational power and storage are virtually possible. Besides, grid services can be accessed everywhere at any time through handtop devices. This research aims at applying the mobile grid technology to the medical line.