期刊
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
卷 51, 期 8, 页码 4716-4728出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSMC.2019.2945053
关键词
Object detection; Feature extraction; Computational modeling; Convolution; Task analysis; Deep learning; Roads; Advanced driver-assistance systems (ADASs); deep learning; lightweight network; modular network; object detection
资金
- National Natural Science Foundation of China [61672286]
- Natural Science Foundation of Jiangsu Province [BK20160842]
This article introduces a modular lightweight network model specifically designed for detecting small objects, addressing the challenges of detecting road objects that are far from the camera and small in size. The proposed network, named modular feature fusion detector (MFFD), utilizes a fast and efficient architecture, demonstrating superiority on the KITTI dataset compared to state-of-the-art methods.
This article presents a modular lightweight network model for road objects detection, such as car, pedestrian, and cyclist, especially when they are far away from the camera and their sizes are small. Great advances have been made for the deep networks, but small objects detection is still a challenging task. In order to solve this problem, a majority of existing methods utilize complicated network or bigger image size, which generally leads to higher computation cost. The proposed network model is referred to as modular feature fusion detector (MFFD), using a fast and efficient network architecture for detecting small objects. The contribution lies in the following aspects: 1) two base modules have been designed for efficient computation: a) Front module reduces the information loss from raw input images and b) Tinier module decreases the model size and computation cost, while ensuring the detection accuracy; 2) by stacking the base modules, we design a context features fusion framework for multiscale object detection; and 3) the proposed method is efficient in terms of model size and computation cost, which is applicable for resource-limited devices, such as embedded systems for advanced driver-assistance systems (ADASs). Comparisons with the state-of-the-art on the challenging KITTI dataset reveal the superiority of the proposed method. Especially, 100 ft/s can be achieved on the embedded GPUs such as Jetson TX2.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据