;Abstract Object tracking has recently been a widely researched topic, specifically in studies investigating computer-automated surveillance systems in the field of computer vision. Among currently available algorithms , the histogram of oriented gradients (HOG) has been recognized as the most effective design. However, in practice, applying the HOG requires excessive computational resources, particularly for the gamma correction method, which is the most time-consuming method. Therefore, by expanding the concept of Sobel edge detection, the present study proposed a feasible real-time computing system named the modified histogram of oriented gradients (MHOG) to minimize the resource requirements of the conventional HOG. Comparing the MHOG and HOG revealed that the proposed algorithm has lower computational resource requirements and enhances the stability of tracking. In this thesis, the differences between the conventional HOG and MHOD are demonstrated in six experimental images, namely images of a water bird, a stationary automobile, a calculator, a moving automobile, and a chimpanzee.
