Performance analysis of a small-scale dynamic platform for target tracking using enlarged template matching

Abstract Vision-based navigation is essential for mobile robotics in dynamic environments. This study develops a four-wheeled robotic platform with an ESP32 camera, Arduino Uno, and mecanum wheels for omnidirectional movement, enabling vision-guided target tracking. The system employs an enlarged template matching method, where image processing is performed on a user computer using a Python-based program. Tracking performance was evaluated using a checkerboard-patterned accuracy board under four template scale values (M = 1.5, 2, 2.5, and 3). Results show that template scale significantly affects tracking accuracy and processing time. The optimal scale (M = 2) achieved 100% accuracy with an average processing time of 24.95 s, while other scales exhibited reduced accuracy due to spatial information loss or noise. This study highlights the effectiveness of enlarged template matching for precise navigation and suggests adaptive template scaling for improved performance. The findings contribute to advancing low-cost, vision-based navigation for mobile robotics.