Saved in:
Bibliographic Details
Main Authors: Dandugula, Gayathri, Boddana, Santhosh, Mirashi, Sudesh
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.07411
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909423188836352
author Dandugula, Gayathri
Boddana, Santhosh
Mirashi, Sudesh
author_facet Dandugula, Gayathri
Boddana, Santhosh
Mirashi, Sudesh
contents Deploying radar object detection models on resource-constrained edge devices like the Raspberry Pi poses significant challenges due to the large size of the model and the limited computational power and the memory of the Pi. In this work, we explore the efficiency of Depthwise Separable Convolutions in radar object detection networks and integrate them into our model. Additionally, we introduce a novel Feature Enhancement and Compression (FEC) module to the PointPillars feature encoder to further improve the model performance. With these innovations, we propose the DSFEC-L model and its two versions, which outperform the baseline (23.9 mAP of Car class, 20.72 GFLOPs) on nuScenes dataset: 1). An efficient DSFEC-M model with a 14.6% performance improvement and a 60% reduction in GFLOPs. 2). A deployable DSFEC-S model with a 3.76% performance improvement and a remarkable 78.5% reduction in GFLOPs. Despite marginal performance gains, our deployable model achieves an impressive 74.5% reduction in runtime on the Raspberry Pi compared to the baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07411
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DSFEC: Efficient and Deployable Deep Radar Object Detection
Dandugula, Gayathri
Boddana, Santhosh
Mirashi, Sudesh
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Deploying radar object detection models on resource-constrained edge devices like the Raspberry Pi poses significant challenges due to the large size of the model and the limited computational power and the memory of the Pi. In this work, we explore the efficiency of Depthwise Separable Convolutions in radar object detection networks and integrate them into our model. Additionally, we introduce a novel Feature Enhancement and Compression (FEC) module to the PointPillars feature encoder to further improve the model performance. With these innovations, we propose the DSFEC-L model and its two versions, which outperform the baseline (23.9 mAP of Car class, 20.72 GFLOPs) on nuScenes dataset: 1). An efficient DSFEC-M model with a 14.6% performance improvement and a 60% reduction in GFLOPs. 2). A deployable DSFEC-S model with a 3.76% performance improvement and a remarkable 78.5% reduction in GFLOPs. Despite marginal performance gains, our deployable model achieves an impressive 74.5% reduction in runtime on the Raspberry Pi compared to the baseline.
title DSFEC: Efficient and Deployable Deep Radar Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.07411