Millions of Muslims from all over the world visit the holy city of Makkah to perform Umrah throughout the year, but especially in the month of Ramadan the quantity of pilgrims increases significantly. Same conditions can be observed in the month of Dhu al-Hijjah during the Hajj season. To transfer the pilgrims from one place to another various many vehicles are used. It is very important to monitor the traffic flow during these days to avoid any congestion which may lead to any mishap. Therefore, there is a need for a traffic flow monitoring system that can be used to count vehicles, and classify them according to their size to facilitate traffic management. A computer vision based system is proposed in this research that uses MATLAB vision tool to identify and count the vehicles. The novelty of the system is its simplicity that uses a camera as a video source, then suitable algorithms are implemented on it for processing. A portion of a video is used for system training that first obtains a binary foreground from the initial frame, then removes noise and then counts the vehicles present in the frame. The functionality of the proposed system has been verified by a number of experiments with the accuracy of 90%. It can be easily implemented in various environments for vehicles counting that can be used for better traffic management.

In this paper, we briefly look at the latest state-ot-the-art in the domain of multi-input multi-output (MIMO) radio frequency identification (RFID) systems while detailing the work done in the domain of anti-collision, range enhancements, bit error rate (BER) improvements and security. Various passive ultra-high frequency (UHF) RFID implementations are considered that employ multiple antennas at the reader and single or multiple antennas at each tag. We look at several recent works those explored MIMO for RFID receivers. When using MIMO at the backscatter channel, significant improvements can be achieved in the BER as well as range extension. With the extra reliability and increased throughput, such systems can be deployed in many important applications like large tag reading scenarios and accurate tracking. Increased throughput is directly dependent on estimation of tag quantity in a bulk reading environment and usually estimators designed for single antenna systems under-perform in such settings causing low signal to noise ratio (SNR) when employed in MIMO systems where tag signal overlapping can happen more often. One of the key challenges is to keep the design of the RFID tag simple, cutting cost and power requirement when employing anti-collision schemes. We provide a brief survey in some of the recent developments related to MIMO RFID systems, the protocols and algorithms used, and improvements achieved.

Radio frequency identification (RFID) technology has been widely used in applications such as access control, inventory management, spatial positioning, and object identification. Accurate tag estimation is one of the major challenges in RFID reader systems particularly in areas where large tag populations are to be identified such as shopping carts, warehouse inventory monitoring, and small ruminant farms. This paper proposes a new tag estimation technique employing artificial neural networks (ANNs) and signal strength to read large tag populations. The technique estimates the number of tags through the signal strength of the backscatter channel for efficient implementation of dynamic framed slotted Aloha (DFSA) protocol by analyzing the RN16 and the received signal strength indicator (RSSI). The ANN model is trained using the signal strength of various tag populations and can identify the number of tags with minimal errors. The proposed technique does not require any modification in the tags and is implemented as a minimal software script to be added to the tag estimation module of the reader. The proposed signal strength-ANN model is able to estimate the accurate number of tags thereby improving the performance of the employed DFSA model.