Yasir Mohd Mustafah

Stereo vision images processing for real-time object distance and size measurements

Human has the ability to roughly estimate the distance and size of an object because of the stereo vision of humans eyes. In this project, we proposed to utilize stereo vision system to accurately measure the distance and size (height and width) of object in view. Object size identification is very useful in building systems or applications especially in autonomous system navigation. Many recent works have started to use multiple vision sensors or cameras for different type of application such as 3D image constructions, occlusion detection and etc. Multiple cameras system has becoming more popular since cameras are now very cheap and easy to deploy and utilize. The proposed measurement system consists of object detection on the stereo images and blob extraction and distance and size calculation and object identification. The system also employs a fast algorithm so that the measurement can be done in real-time. The object measurement using stereo camera is better than object detection using a single camera that was proposed in many previous research works. It is much easier to calibrate and can produce a more accurate results.

Face detection system design for real time high resolution smart camera

Recognizing faces in a crowd in real-time is a key feature which would significantly enhance Intelligent Surveillance Systems. Using a smart camera as a tool to extract faces for recognition would greatly reduce the computational load on the main processing unit. Main processing unit would not be overloaded by the demands of the high data rates of the video and could be designed solely for face recognition. The challenge is with the increasing speed and resolution of the camera sensors, a fast and robust face detection system is required for real time operation. In this paper we report on a multiple-stage face detection system that is designed for implementation on an FPGA based high resolution smart camera system. The system consist of filter stages to greatly reduce the region of interest in video image, followed by a face detection stage to accurately locate the faces. For filter stage, the algorithm is designed to be very fast so that it can be processed in real time. Meanwhile, for face detection stage, a hardware and software co-design technique is utilised to accelerate it.

An Automated Face Recognition System for Intelligence Surveillance: Smart Camera Recognizing Faces in the Crowd

Smart cameras are rapidly finding their way into intelligent surveillance systems. Recognizing faces in the crowd in real-time is one of the key features that will significantly enhance intelligent surveillance systems. The main challenge is the fact that the high volumes of data generated by high-resolution sensors make it computationally impossible for mainstream computers to process. In our proposed technique, the smart camera extracts all the faces from the full-resolution frame and sends the pixel information from these face areas to the main processing unit as a auxiliary video stream - potentially achieving massive data rate reduction. Face recognition software running on the main processing unit then performs the required pattern recognition.

Real-Time Face Detection and Tracking for High Resolution Smart Camera System

Smart Cameras are becoming more popular in Intelligent Surveillance Systems area. Recognizing faces in a crowd in real-time is a key features which would significantly enhance Intelligent Surveillance Systems. Using a high resolution smart camera as a tool to extract faces that are suitable for face recognition would greatly reduce the computational load on the main processing unit. This processing unit would not be overloaded by the demands of the high data rates required for high resolution video and could be designed solely for face recognition. In this paper we report on a multiple-stage face detection and tracking system that is designed for implementation on the NICTA high resolution (5 MP) smart camera.

Performance Comparison between RGB and HSV Color Segmentations for Road Signs Detection

This paper compares the performance of RGB and HSV color segmentations method in road signs detection. The road signs images are taken under various illumination changes, partial occlusion and rotational changes. The proposed algorithms using both RGB and HSV color space are able to detect the 3 standard types of colored images namely Red, Yellow and Blue. The experiment shows that the HSV color algorithm achieved better detection accuracy compared to RGB color space.

Colour-based Object Detection and Tracking for Autonomous Quadrotor UAV

With robotics becoming a fundamental aspect of modern society, further research and consequent application is ever increasing. Aerial robotics, in particular, covers applications such as surveillance in hostile military zones or search and rescue operations in disaster stricken areas, where ground navigation is impossible. The increased visual capacity of UAVs (Unmanned Air Vehicles) is also applicable in the support of ground vehicles to provide supplies for emergency assistance, for scouting purposes or to extend communication beyond insurmountable land or water barriers. The Quadrotor, which is a small UAV has its lift generated by four rotors and can be controlled by altering the speeds of its motors relative to each other. The four rotors allow for a higher payload than single or dual rotor UAVs, which makes it safer and more suitable to carry camera and transmitter equipment. An onboard camera is used to capture and transmit images of the Quadrotors First Person View (FPV) while in flight, in real time, wirelessly to a base station. The aim of this research is to develop an autonomous quadrotor platform capable of transmitting real time video signals to a base station for processing. The result from the image analysis will be used as a feedback in the quadrotor positioning control. To validate the system, the algorithm should have the capacity to make the quadrotor identify, track or hover above stationary or moving objects.

Optimizing Resources of an FPGA-based Smart Camera Architecture

The acceptance of reconfigurable platforms specifically FPGAs in embedded system design is becoming more apparent. While there are varieties of platforms available for smart camera implementation, our interest is mainly on reconfigurable platforms, specifically FPGAs. In this paper we discuss the research opportunity and the importance of hardware/software partitioning on FPGA-based smart camera platform. An overview of our current research work on the above mentioned problem is describe in this paper.

Face recognition using illumination-invariant local patches

Illumination variation that span globally and locally across the facial surface is one of the most important aspect in designing a robust face recognition system. The illumination variations due to changes in lighting conditions could produce different shape of shading on the face thus deforming the facial features. The effect of these variations is simply more severe in the presence of single-sample constraint since there would be many variables with very limited observations. Illumination variations have been modelled in literature as a series of undetermined multiplicative and additive noise, hence it is more convenient to eliminate or reduce the effect rather than computing them. In this paper, we present an illumination-invariant method where we use local features as basis for face classification which is obtained from partitioning histogram-equalized faces into smaller overlapping local patches (LPs). We can achieve illumination-invariance for these LPs by subtracting the vectors with local average illumination and then these vectors are logarithmically normalized to enhance the local contrast. The degree of invariance is controlled by a weight connected to the average intensity component. We have tested this method in single sample face recognition setting on AR Database and Extended YALE B Database. Recognition results show that the proposed method is suitable for robust face recognition since it achieve good performance in both even illumination and uneven illumination cases.

Autonomous Navigation of Mobile Robot Using Kinect Sensor

The problem of achieving real time process in depth camera application, in particular when used for indoor mobile robot localization and navigation is far from being solved. Thus, this paper presents autonomous navigation of the mobile robot by using Kinect sensor. By using Microsoft Kinect XBOX 360 as the main sensor, the robot is expected to navigate and avoid obstacles safely. By using depth data, 3D point clouds, filtering and clustering process, the Kinect sensor is expected to be able to differentiate the obstacles and the path in order to navigate safely. Therefore, this research requirement to propose a creation of low-cost autonomous mobile robot that can be navigated safely.

Low voltage DC power supply with spike-blocking features

RFID tags, sensors embedded with buried devices and biomedical implants all operate at low voltage levels due to power limitations. The ever increasing use these embedded devices has also created a demand in the industry for low-voltage power supplies. Since many of these circuits are mobile in nature and so are bound to operate in many different environments, the power supply must also be capable of ensuring a stable voltage output even under adverse conditions. This paper analyzes and simulates a power supply circuit that promises a low ripple factor with an element of spike-blocking capability. It centers on a phase-modulation technique that effectively cancels out 99.6% of ripples when operating with a 100 mV ac input at a frequency of 10 kHz. This active noise-cancellation technique allows for a more stable voltage output. It also has a limited inbuilt capability to block spikes. A 100 mV injected spike is brought down to only 6 mV without the use of other damping circuits. This work is therefore capable of damping a large part of the variations in the input voltage, even at low voltages.