Vehicle Counting and Detection

This paper describes about the system to count the number of vehicles on roads and highways by using adaptive background subtraction and blob tracking technologies. Overall, system requires a video stream captured from static cameras installed on roads and highways .The proposed system consists of four stages: 1) Adaptive background subtraction 2) image segmentation 3) vehicle counting 4) vehicle tracking. The necessity of tracing and counting the vehicles is helpful for traffic surveillance. The primary key features of the system are 1) Ability to count the vehicles 2) efficiency, to show that system would give the results with high perfection.

An Improved Mixture-of-Gaussians Background Model with Frame Difference and Blob Tracking in Video Stream

Modeling background and segmenting moving objects are significant techniques for computer vision applications. Mixture-of-Gaussians (MoG) background model is commonly used in foreground extraction in video steam. However considering the case that the objects enter the scenery and stay for a while, the foreground extraction would fail as the objects stay still and gradually merge into the background. In this paper, we adopt a blob tracking method to cope with this situation. To construct the MoG model more quickly, we add frame difference method to the foreground extracted from MoG for very crowded situations. What is more, a new shadow removal method based on RGB color space is proposed.

Auto Pan Tilt Motion Surveillance System

Projek ini bertujuan untuk membangunkan satu sistem yang dilengkapi dengan pelbagai jenis jejakkan. Sistem tersebut kecil dari segi saiz, mudah alih dan memudahkan pemasangan. Konvensyen sistem terdiri daripada fungsi operasi tunggal dan mempunyai sistem yang besar. Projek ini boleh dicapai dengan pemasangan webcam murah dengan dua motor servo yang memainkan peranan sebagai sendi gerakan. Gerakan tersebut berdasarkan proses menarik dan mendorong dengan sambungan yang terlekat pada motor. Sistem tersebut mampu melakukan tugas pengesanan objek, jejakkan warna dan jejakkan gumpalan warna cahaya laser. Selain itu, video rakaman, gambar tangkapan dan pencetusan penggera boleh dilakukan. Sistem pelbagai fungsi ini dibangunkan dengan algoritma gabungan dari pelbagai jenis penapis. Alat tersebut telah dicuba dalam keadaan bilik dan keadaan luaran. Kajian menunjukkan sistem mampu mengkompensasi dengan gangguan hingar. Sistem tersebut mampu mencapai kelajuan 0.125 ms–1 dengan 145° dan 60° periuk gerakan miring. Pemasangan system tersebut melibatkan kos yang murah dan boleh diaplikasikan dalam robot visi, persidangan video dan aplikasi UAV automatik. Kata kunci: Pengesanan gerakan; pelacakan gumpalan warna; pelacakan laser; sistem pemantauan pintar; kamera pelacakan objek This research develops webcam base pan and tilt camera with multiple tracking ability. This pan tilt surveillance system is small in size, portable and easy for installation. Convention surveillance system is limited to single function operation and have bulky camera system. The key component of this surveillance system is the attachment of low cost webcam onto pan and tilt servo motor. The movement of the webcam results from pulls and push coupling unit which attach to the motor. The smart surveillance system able to perform motion detection task, color blob tracking and laser light tracking. Automatic system enhanced its ability into real–time auto motion video record, photo snap shot and trigger alarm. This multi function system is developed with improve algorithm combination from different type of multi–filter. It is experimented under indoor and outdoor environment. The result shows the system able to compensate with the noise disturbance. The reported maximum speed is 0.125 ms–1 with 145° pan movement and 60° tilt movements. Such automated system is cost effective and can be used as robot vision, automated video conference and UAV application. Key words: Motion detection; color blob tracking; laser tracking; smart surveillance system; object tracking camera