LEOD-Net: Learning Line-Encoded Bounding Boxes for Real-Time Object Detection
This paper proposes a learnable line encoding technique for bounding boxes commonly used in the object detection task. A bounding box is simply encoded using two main points: the top-left corner and the bottom-right corner of the bounding box; then, a lightweight convolutional neural network (CNN) i...
Main Authors: | Hatem Ibrahem, Ahmed Salem, Hyun-Soo Kang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/10/3699 |
Similar Items
-
SDDS-Net: Space and Depth Encoder-Decoder Convolutional Neural Networks for Real-Time Semantic Segmentation
by: Hatem Ibrahem, et al.
Published: (2023-01-01) -
DTS-Net: Depth-to-Space Networks for Fast and Accurate Semantic Object Segmentation
by: Hatem Ibrahem, et al.
Published: (2022-01-01) -
Accurate and Lightweight RailNet for Real-Time Rail Line Detection
by: Zhen Tao, et al.
Published: (2021-08-01) -
A Deep-Learning Model with Task-Specific Bounding Box Regressors and Conditional Back-Propagation for Moving Object Detection in ADAS Applications
by: Guan-Ting Lin, et al.
Published: (2020-09-01) -
RCDAM-Net: A Foreign Object Detection Algorithm for Transmission Tower Lines Based on RevCol Network
by: Wenli Zhang, et al.
Published: (2024-01-01)