Copyright © 2018 Budi Setiyono et. al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. International Journal of Engineering & Technology, 7 (4) (2018) 2515-2520 International Journal of Engineering & Technology Website: www.sciencepubco.com/index.php/IJET doi: 10.14419/ijet.v7i4.13725 Research paper Improvement of sub region matching illumination transfer in hybrid shadow removal method for moving vehicle video Budi Setiyono 1 *, Dwi Ratna Sulistyaningrum 1 , Soetrisno 1 , Hasanuddin Al-Habib 1 1 Department of Mathematics, Institut Teknologi Sepuluh Nopember, Kampus ITS Sukolilo Surabaya 60111, Indonesia *Corresponding author E-mail: masbudisetiyono@gmail.com Abstract Intelligent Transportation System (ITS) is a concept to manage transportation based on technology development. Video from surveil- lance cameras can be used for monitoring the number of vehicles and speed using digital image processing. Shadows on the vehicle is one of the noise that must be removed in order to obtain better accuracy. Shadow is caused by the reflection of objects exposed to the light. In this study, we combined two methods to eliminate shadows on moving vehicle, the subregion illumination transfer method and the background-based Gaussian mixture model. Foreground image is used for sub-Region Illumination Transfer and gamma decoding processes is used to detect the presence of shadows The detected shadow is removed by replacing it with the background in that position. Experiments are done by making simulated video of moving objects without shadows and objects that have a shadow. By using the pro- posed method, the shadow will be omitted, and the results are compared with the object without the shadow. The experimental results are: mean value of PSNR for objects moving closer to the camera with a light intensity of 0.8 is 53.47. While on the moving object with a small shadow area, we obtained an average PSNR of 51.87927dB. Keywords: Shadow Removal; Gaussian Mixture Model; Gamma-Decoding Method; Intelligent Transportation System; Moving Object. 1. Introduction Along with government policies in accelerating the develoment of infrastructure, the smart cities are developed very rapidly. One of the supporting factor of smart city is the Intelligent Transportation Systems (ITS). In ITS, automation in traffic management plays an important role. Vehicle calculations and estimated vehicle speed are among the examples that can be done automatically. The main obstacle in vehicle transportation is the presence of shadows due to the influence of sunlight. Therefore, this research is quite im- portant as to support the development of ITS. Intelligent Transportation System (ITS) is a concept which is part of smart city system that works for transportation management. ITS as a digital highway management and monitoring system generally utilizes digital-based CCTV (Closed Circuit Television) cameras. Video from surveillance cameras can be used for moni- toring the number of vehicles and speed using digital image pro- cessing. Shadows on the vehicle is one of the noise that must be removed in order to obtain better accuracy. This results in an error in the introduction of the object because often the shadow consid- ered as part of the object. So the information obtained becomes less and not as expected. In digital imaging, the shadow is an area affected by a lighting change. In other words when the object is placed between the light source and the background surface, the object will block the light to get to the background surface. Basically shadow consists of two categories, namely umbra and penumbra. Based on the the above conditions, the shadow is one of the noise in a video or digital image that affected to the accuracy of image recognition or object counting. So the special treatment is needed to eliminate the shad- ow. Shadow removal was investigated using the Subregion Matching Illumination Transfer method, but only for single input In addi- tion, one of the weaknesses of this method is that when used for image data that has a complex structure, such as the variations of umbra, penumbra, and various non-uniform color structures, and the conditions of illumination are varied, then this method needs further development [1]. Some previous other research related to this topic were conducted by Chin-Teng Lin in 2010 using Gauss- ian Mixture Model method as substraction method background and foreground and this research is done with uniform light distri- bution [2 – 5]. The shadow elimination for moving objects by updating the Gaussian parameters was also carried out in the re- search of Budi Setiyono et al [6 – 8]. Mohamad Toha et al, re- searches to remove the shadow of moving objects by estimating the image foreground with different frame and applying the gam- ma decoding method to segment the shaded area and object area [9] [10]. Gaussian Mixture Model is also used as the basic for tracking the vehicle and obtained accurate results [11]. Another study of shadow removal in moving object is done by combining the averaging method and Gaussian mixture model as subtraction method for background and foreground in HSV colour space. In this paper, we apply Gaussian mixture model to obtain the RGB background as the input of gamma decoding method to segment shadow pixels and object pixels from a frame of digital video [12], [13]. This paper is structured as follows: The proposed method of im- provement of sub region matching illumination Transfer is ex- plained in Section 2. In Section 3, we will present the experiment