# A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices

arXiv: https://arxiv.org/abs/2409.16808 · HTML: https://mlsanity.com/paper/2409.16808/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Builds on (most cited first, 10 of 10)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [MobileDets: Searching for Object Detection Architectures for Mobile Accelerators](https://mlsanity.com/paper/2004.14525/) (2020)
- [DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices](https://mlsanity.com/paper/2108.09457/) (2021)
- [Object Detection in Autonomous Vehicles: Status and Open Challenges](https://mlsanity.com/paper/2201.07706/) (2022)
- [Benchmarking Edge Computing Devices for Grape Bunches and Trunks Detection using Accelerated Object Detection Single Shot MultiBox Deep Learning Models](https://mlsanity.com/paper/2211.11647/) (2022)

## Built on by (most cited first, 6 of 6)

- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [A Comprehensive Evaluation of YOLO-based Deer Detection Performance on Edge Devices](https://mlsanity.com/paper/2509.20318/) (2025)
- [Development and Testing for Perception Based Autonomous Landing of a Long-Range QuadPlane](https://mlsanity.com/paper/2512.09343/) (2025)
- [HitoMi-Cam: A Shape-Agnostic Person Detection Method Using the Spectral Characteristics of Clothing](https://mlsanity.com/paper/2511.08908/) (2025)
- [Towards automatic smoke detector inspection: Recognition of the smoke detectors in industrial facilities and preparation for future drone integration](https://mlsanity.com/paper/2603.24850/) (2026)
- [Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Accelerators](https://mlsanity.com/paper/2609.16085/) (2026)

## Abstract (arXiv)

Modern applications such as autonomous vehicles, intelligent surveillance, and smart city systems increasingly require object detection on resource-constrained edge devices. Yet, there is still limited understanding of how different object detection models behave across heterogeneous edge devices and under varying scene complexity. In this paper, we benchmark YOLOv8 (Nano, Small, Medium), EfficientDet Lite (Lite0, Lite1, Lite2), and SSD (SSD MobileNet V1, SSDLite MobileDet) on Raspberry Pi 3, 4, 5 with/without Coral TPU accelerators, Raspberry Pi 5 with AI HAT+, Jetson Nano, and Jetson Orin Nano. We evaluate energy consumption, inference time, and accuracy, and further examine how accuracy changes with the number of objects in the input image. The results reveal clear trade-offs among accuracy, latency, and energy efficiency across model-device combinations. SSD MobileNet V1 achieves the lowest latency and energy consumption but the lowest accuracy, whereas YOLOv8 Medium achieves the highest accuracy at higher computational cost. TPU-based Raspberry Pi devices improve the efficiency of SSD and EfficientDet Lite while reducing YOLOv8 accuracy. Orin Nano offers the most favorable overall balance across most model families. The object-count-based analysis further shows that models achieve more similar accuracy on simpler images, while the accuracy gap widens as scene complexity increases.