Light-Weight Edge Enhanced Network for On-orbit Semantic Segmentation

2019 ◽  
pp. 321-333
Author(s):  
Junxing Hu ◽  
Ling Li ◽  
Yijun Lin ◽  
Fengge Wu ◽  
Junsuo Zhao
Keyword(s):  
Semantic Segmentation ◽  
Light Weight

scholarly journals PlaneNet: an efficient local feature extraction network

2021 ◽  
Vol 7 ◽  
pp. e783
Author(s):  
Bin Lin ◽  
Houcheng Su ◽  
Danyang Li ◽  
Ao Feng ◽  
Hongxiang Li ◽  
...  
Keyword(s):  
Mobile Devices ◽  
State Of The Art ◽  
Computing Time ◽  
Semantic Segmentation ◽  
Vital Role ◽  
Light Weight ◽  
Practical Application ◽  
Classification Tasks ◽  
Segmentation Task ◽  
Local Feature Extraction

Due to memory and computing resources limitations, deploying convolutional neural networks on embedded and mobile devices is challenging. However, the redundant use of the 1 × 1 convolution in traditional light-weight networks, such as MobileNetV1, has increased the computing time. By utilizing the 1 × 1 convolution that plays a vital role in extracting local features more effectively, a new lightweight network, named PlaneNet, is introduced. PlaneNet can improve the accuracy and reduce the numbers of parameters and multiply-accumulate operations (Madds). Our model is evaluated on classification and semantic segmentation tasks. In the classification tasks, the CIFAR-10, Caltech-101, and ImageNet2012 datasets are used. In the semantic segmentation task, PlaneNet is tested on the VOC2012 datasets. The experimental results demonstrate that PlaneNet (74.48%) can obtain higher accuracy than MobileNetV3-Large (73.99%) and GhostNet (72.87%) and achieves state-of-the-art performance with fewer network parameters in both tasks. In addition, compared with the existing models, it has reached the practical application level on mobile devices. The code of PlaneNet on GitHub: https://github.com/LinB203/planenet.

scholarly journals Deep Ego-Motion Classifiers for Compound Eye Cameras

Sensors ◽  
2019 ◽  
Vol 19 (23) ◽  
pp. 5275
Author(s):  
Hwiyeon Yoo ◽  
Geonho Cha ◽  
Songhwai Oh
Keyword(s):  
Compound Eye ◽  
Semantic Segmentation ◽  
Field Of View ◽  
Large Field ◽  
Light Weight ◽  
Unique Form ◽  
Motion Classification ◽  
Proposed Model ◽  
Compound Images ◽  
High Level

Compound eyes, also known as insect eyes, have a unique structure. They have a hemispheric surface, and a lot of single eyes are deployed regularly on the surface. Thanks to this unique form, using the compound images has several advantages, such as a large field of view (FOV) with low aberrations. We can exploit these benefits in high-level vision applications, such as object recognition, or semantic segmentation for a moving robot, by emulating the compound images that describe the captured scenes from compound eye cameras. In this paper, to the best of our knowledge, we propose the first convolutional neural network (CNN)-based ego-motion classification algorithm designed for the compound eye structure. To achieve this, we introduce a voting-based approach that fully utilizes one of the unique features of compound images, specifically, the compound images consist of a lot of single eye images. The proposed method classifies a number of local motions by CNN, and these local classifications which represent the motions of each single eye image, are aggregated to the final classification by a voting procedure. For the experiments, we collected a new dataset for compound eye camera ego-motion classification which contains scenes of the inside and outside of a certain building. The samples of the proposed dataset consist of two consequent emulated compound images and the corresponding ego-motion class. The experimental results show that the proposed method has achieved the classification accuracy of 85.0%, which is superior compared to the baselines on the proposed dataset. Also, the proposed model is light-weight compared to the conventional CNN-based image recognition algorithms such as AlexNet, ResNet50, and MobileNetV2.

scholarly journals CGNet: A Light-Weight Context Guided Network for Semantic Segmentation

2021 ◽  
Vol 30 ◽  
pp. 1169-1179
Author(s):  
Tianyi Wu ◽  
Sheng Tang ◽  
Rui Zhang ◽  
Juan Cao ◽  
Yongdong Zhang
Keyword(s):  
Semantic Segmentation ◽  
Light Weight

scholarly journals LAENet: Light-weight asymmetric encoder-decoder network for semantic segmentation

2021 ◽  
Vol 1966 (1) ◽  
pp. 012047
Author(s):  
Liangyi Hong ◽  
Shukai Duan ◽  
Lidan Wang ◽  
Yongbin Pan
Keyword(s):  
Semantic Segmentation ◽  
Light Weight

Semantic Segmentation for High-Resolution Remote Sensing Images by Light-Weight Network

2021 ◽  
Author(s):  
Changjian Deng ◽  
Leikun Liang ◽  
Yanzhou Su ◽  
Changtao He ◽  
Jian Cheng
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Semantic Segmentation ◽  
Light Weight ◽  
Remote Sensing Images
Sign in / Sign up

Export Citation Format

Share Document