paper-with-me

홈 › Papers

Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml

2022-05-16 · Nicolò Ghielmetti, Vladimir Loncar, Maurizio Pierini, Marcel Roed, Sioni Summers, Thea Aarrestad, Christoffer Petersson, Hampus Linander, Jennifer Ngadiuba, Kelvin Lin, Philip Harris

In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural network architecture, we demonstrate a fully-on-chip deployment with a latency of 4.9 ms per image, using less than 30% of the available resources on a Xilinx ZCU102 evaluation board. The latency is reduced to 3 ms per image when increasing the batch size to ten, corresponding to the use case where the autonomous vehicle receives inputs from multiple cameras simultaneously. We show, through aggressive filter reduction and heterogeneous quantization-aware training, and an optimized implementation of convolutional layers, that the power consumption and resource utilization can be significantly reduced while maintaining accuracy on the Cityscapes dataset.

📄 PDF Abstract BibTeX arXiv:2205.07690

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingAutonomous VehiclesQuantizationReal-Time Semantic SegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

SpatialDropout SpatialDropout is a type of dropout for convolutional networks. For a given…
Dilated Convolution 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Batch Normalization 설명 없음
PReLU A Parametric Rectified Linear Unit, or PReLU, is an activation function that generalizes the traditional rectified unit with a slope for negative values.…
ENet Initial Block The ENet Initial Block is an image model block used in the ENet semantic segmentation architecture. [Max…
ENet Dilated Bottleneck ENet Dilated Bottleneck is an image model block used in the ENet semantic segmentation architecture. It is the same as a regular…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems

2026-07-02 · Uwe M. Borghoff, Paolo Bottoni, Remo Pareschi arxiv

Recent advances in agentic AI are producing increasingly complex autonomous systems that integrate large language models, world models, optimization engines, specialized neural architectures, autonomous platforms, and hu…

SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud

2024-06-24 · Neng Wang, Ruibin Guo, Chenghao Shi, Ziyue Wang 외

4D LiDAR semantic segmentation, also referred to as multi-scan semantic segmentation, plays a crucial role in enhancing the environmental understanding capabilities of autonomous vehicles or robots. It classifies the sem…

Autonomous DrivingAutonomous NavigationAutonomous VehiclesLIDAR Semantic Segmentation+2

FPGA based Parallelized Architecture of Efficient Graph based Image Segmentation Algorithm

2017-10-06 · Roopal Nahar, Akanksha Baranwal, K. Madhava Krishna

Efficient and real time segmentation of color images has a variety of importance in many fields of computer vision such as image compression, medical imaging, mapping and autonomous navigation. Being one of the most comp…

Autonomous NavigationImage CompressionImage SegmentationSegmentation+1

PCSCNet: Fast 3D Semantic Segmentation of LiDAR Point Cloud for Autonomous Car using Point Convolution and Sparse Convolution Network

2022-02-21 · JaeHyun Park, Chansoo Kim, Kichun Jo

The autonomous car must recognize the driving environment quickly for safe driving. As the Light Detection And Range (LiDAR) sensor is widely used in the autonomous car, fast semantic segmentation of LiDAR point cloud, w…

3D Semantic SegmentationSegmentationSemantic Segmentation

Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images

2020-02-24 · Lei Sun, Kailun Yang, Xinxin Hu, Weijian Hu 외

Semantic segmentation has made striking progress due to the success of deep convolutional neural networks. Considering the demands of autonomous driving, real-time semantic segmentation has become a research hotspot thes…

Autonomous DrivingAutonomous VehiclesReal-Time Semantic SegmentationSegmentation+1