# Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video

arXiv: https://arxiv.org/abs/1709.05943 · HTML: https://mlsanity.com/paper/1709.05943/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2017.

## Built on by (most cited first, 30 of 30)

- [Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey](https://mlsanity.com/paper/2108.11510/) (2021)
- [Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2112.03328/) (2021)
- [Breaking reCAPTCHAv2](https://mlsanity.com/paper/2409.08831/) (2024)
- [YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs](https://mlsanity.com/paper/2110.13713/) (2021)
- [FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors](https://mlsanity.com/paper/2303.08319/) (2023)
- [VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments](https://mlsanity.com/paper/2408.02454/) (2024)
- [Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture](https://mlsanity.com/paper/2207.05605/) (2022)
- [Parallel Detection for Efficient Video Analytics at the Edge](https://mlsanity.com/paper/2107.12563/) (2021)
- [Attacking Object Detector Using A Universal Targeted Label-Switch Patch](https://mlsanity.com/paper/2211.08859/) (2022)
- [Table Detection for Visually Rich Document Images](https://mlsanity.com/paper/2305.19181/) (2023)
- [FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs](https://mlsanity.com/paper/2301.06719/) (2023)
- [Bridging Gap between Image Pixels and Semantics via Supervision: A Survey](https://mlsanity.com/paper/2107.13757/) (2021)
- [Real-time Bangla License Plate Recognition System for Low Resource Video-based Applications](https://mlsanity.com/paper/2108.08339/) (2021)
- [Towards Efficient Single Image Dehazing and Desnowing](https://mlsanity.com/paper/2204.08899/) (2022)
- [Revisiting Table Detection Datasets for Visually Rich Documents](https://mlsanity.com/paper/2305.04833/) (2023)
- [Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMS](https://mlsanity.com/paper/2310.13951/) (2023)
- [SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition](https://mlsanity.com/paper/2409.20083/) (2024)
- [A Review of Modern Approaches for Coronary Angiography Imaging Analysis](https://mlsanity.com/paper/2209.13997/) (2022)
- [Advanced Efficient Strategy for Detection of Dark Objects Based on Spiking Network with Multi-Box Detection](https://mlsanity.com/paper/2310.06370/) (2023)
- [Object Recognition Datasets and Challenges: A Review](https://mlsanity.com/paper/2507.22361/) (2025)
- [Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks](https://mlsanity.com/paper/2104.04255/) (2021)
- [Estimating the Power Consumption of Heterogeneous Devices when performing AI Inference](https://mlsanity.com/paper/2207.06150/) (2022)
- [3DFusion, A real-time 3D object reconstruction pipeline based on streamed instance segmented data](https://mlsanity.com/paper/2311.06659/) (2023)
- [Holistic Interpretation of Public Scenes Using Computer Vision and Temporal Graphs to Identify Social Distancing Violations](https://mlsanity.com/paper/2112.06428/) (2021)
- [Identifying the exterior image of buildings on a 3D map and extracting elevation information using deep learning and digital image processing](https://mlsanity.com/paper/2201.01081/) (2022)
- [Recent Trends in 2D Object Detection and Applications in Video Event Recognition](https://mlsanity.com/paper/2202.03206/) (2022)
- [Lightweight Graph Convolutional Networks with Topologically Consistent Magnitude Pruning](https://mlsanity.com/paper/2203.13616/) (2022)
- [Scoliosis Detection using Deep Neural Network](https://mlsanity.com/paper/2210.17269/) (2022)
- [CNN-based Dendrite Core Detection from Microscopic Images of Directionally Solidified Ni-base Alloys](https://mlsanity.com/paper/2305.12506/) (2023)
- [A Hybrid Framework of Vision Transformer and Gated Recurrent Unit for Detection of Mosquito Diseases](https://mlsanity.com/paper/2608.11582/) (2026)

## Abstract (arXiv)

Object detection is considered one of the most challenging problems in this field of computer vision, as it involves the combination of object classification and object localization within a scene. Recently, deep neural networks (DNNs) have been demonstrated to achieve superior object detection performance compared to other approaches, with YOLOv2 (an improved You Only Look Once model) being one of the state-of-the-art in DNN-based object detection methods in terms of both speed and accuracy. Although YOLOv2 can achieve real-time performance on a powerful GPU, it still remains very challenging for leveraging this approach for real-time object detection in video on embedded computing devices with limited computational power and limited memory. In this paper, we propose a new framework called Fast YOLO, a fast You Only Look Once framework which accelerates YOLOv2 to be able to perform object detection in video on embedded devices in a real-time manner. First, we leverage the evolutionary deep intelligence framework to evolve the YOLOv2 network architecture and produce an optimized architecture (referred to as O-YOLOv2 here) that has 2.8X fewer parameters with just a ~2% IOU drop. To further reduce power consumption on embedded devices while maintaining performance, a motion-adaptive inference method is introduced into the proposed Fast YOLO framework to reduce the frequency of deep inference with O-YOLOv2 based on temporal motion characteristics. Experimental results show that the proposed Fast YOLO framework can reduce the number of deep inferences by an average of 38.13%, and an average speedup of ~3.3X for objection detection in video compared to the original YOLOv2, leading Fast YOLO to run an average of ~18FPS on a Nvidia Jetson TX1 embedded system.