Surveillance cameras play a vital role in a wide range of monitoring applications, particularly in ensuring real-time security and observation. However, conventional surveillance systems often face limitations in energy efficiency, especially when deployed in remote locations or powered by battery sources. Although many surveillance cameras offer high-resolution capabilities, only a few incorporate power management strategies to optimize energy usage. The research presents the design and implementation of a low-power surveillance camera system based on the ESP32-CAM platform, incorporating a sleep mode to enhance power efficiency. Two operational scenarios are tested: one with enabled sleep mode and one without. Experimental results show that the camera without sleep mode achieves a higher frame rate of up to 17.01 FPS than the sleep-enabled camera with a maximum of 3.53 FPS. Despite the reduced frame rate, the system successfully performs object detection using the YOLOv3 model processed via edge computing. Furthermore, the average wake-up time from sleep mode is 1.414 seconds, indicating a fast, responsive system suitable for low-power embedded applications. In terms of energy consumption, the sleep-enabled device consumes only 3475.543 mW over 2 hours of operation, compared to 5561.639 mW for the device without sleep mode, resulting in an energy saving of approximately 37.5%. These findings confirm that implementing sleep mode is effective in managing power consumption without compromising core surveillance functionality. The research contributes to the development of sustainable and energy-efficient monitoring solutions and highlights the potential for further enhancement through advanced edge computing platforms in future work.
Copyrights © 2026