234 research outputs found
Development of non-contact liquid level measurement and data storage system
No full textThe normal contact type liquid measurement devices have some drawbacks since they have potential damage due to the sensor fouling or corrosion since those are continuously exposed to the liquid. Especially flash flood may cause the damage of liquid level sensor. So that, it is important to design a non-contact device for liquid level measurement in order to avoid this constrain. Distance can be measured without contact such as laser, ultrasonic and radar. In this research, ultrasonic sensor is used to provide non-contact feature of the device since it is low cost and uses ultra-sound waves rather than light. This vital sensing device is able to sense uneven surfaces, liquids, clear objects, and objects in dirty environments. This paper discussed the measurement of liquid level in a tank as well as storing historical data
Real-time vehicle counting using custom YOLOv8n and DeepSORT for resource-limited edge devices
No full textRecently, there has been a significant increase in the use of deep learning and low-computing edge devices for analysis of video-based systems, particularly in the field of intelligent transportation systems (ITS). One promising application of computer vision techniques in ITS is in the development of low-computing and accurate vehicle counting systems that can be used to eliminate dependence on external cloud computing resources. This paper proposes a compact, reliable and real-time vehicle counting solution which can be deployed on low-computational requirement edge computing devices. The system makes use of a custom-built vehicle detection algorithm based on the you only look once version 8 nano (YOLOv8n), combined with a deep association metric (DeepSORT) object tracking algorithm and an efficient vehicle counting method for accurate counting of vehicles in highway scenes. The system is trained to detect, track and count four distinct vehicle classeses, namely: car, motorcycle, bus, and truck. The proposed system was able to achieve an average vehicle detection mean average precision (mAP) score of 97.5%, a vehicle counting accuracy score of 96.8% and an average speed of 19.4 frames per second (FPS), all while being deployed on a compact Nvidia Jetson Nano edge-computing device. The proposed system outperforms other previously proposed tools in terms of both accuracy and speed
Design and application of intelligent fuzzy controller on a quarter car suspension system
No full text
Development of omni directional mobile robot navigation system using RFID
No full textA present a modular navigation technique in relation with the signal from RFID tags, and RFID reader. We will come out with the simplest circuit and micro-controller to navigate the identification number on RFID tags. The main idea is to test the ability of mobile robot to navigate the location in indoor environments. The RFID reader is mounted on the mobile robot to communicate with the RFID tags to determine robot's position while the RFID tags are attached at different location. The position of mobile robot is determined according to the location of FRID tag. The actuator will be moved according to the angle between the robot's current position and target ta
Development of auto parking system & auto billing system using image processing technique (Part 1)
No full text- …
