Performance Analysis of Container Technologies for Computer Vision Applications on Edge Devices

In the dynamic realm of technology, various container technologies offer efficient deployment and resource utilization in edge devices. However, limited research has explored how various container technologies perform in specific domains. In response, this paper addresses this gap by evaluating container technologies like RunC, LXC, Containerd, Docker, Podman, and Singularity in OpenCV-based computer vision applications on ARM-based edge devices. Results show comparable performance between containerized and non-containerized applications. Containerd excels in memory reading, with both Containerd and LXC efficient in wired image reception, while Singularity and Containerd lead in wireless image reception. Despite Docker’s slower memory reading, its consistently faster processing time positions it as a competitive option. Overall, Docker demonstrates superior efficiency for computer vision applications on ARM-based edge devices. These insights contribute to bridge the existing gap in integrating containers into IoT and ARM-based edge computing scenarios.