Light-Weight Edge Enhanced Network for On-orbit Semantic Segmentation
| Autor: | Fengge Wu, Junxing Hu, Junsuo Zhao, Ling Li, Yijun Lin |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Pattern recognition 02 engineering and technology Filter (signal processing) 010501 environmental sciences 01 natural sciences Image (mathematics) Transmission (telecommunications) Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Enhanced Data Rates for GSM Evolution Artificial intelligence business Pruning (morphology) Aerial image 0105 earth and related environmental sciences |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030304836 ICANN (2) |
| DOI: | 10.1007/978-3-030-30484-3_27 |
| Popis: | On-orbit semantic segmentation can produce the target image tile or image description to reduce the pressure on transmission resources of satellites. In this paper, we propose a fully convolutional network for on-orbit semantic segmentation, namely light-weight edge enhanced network (LEN). For the model to be pruned, we present a new model pruning strategy based on unsupervised clustering. The method is performed according to the \(l_1\)-norm of each filter in the convolutional layer. And it effectively guides the pruning of filters and corresponding feature maps in a short time. In addition, the LEN uses a trainable edge enhanced module called enhanced domain transform to further optimize segmentation performance. The module fully exploits multi-level information of the object to generate the edge map and performs edge-preserving filtering on the coarse segmentation. Experimental results suggest that the models produce competitive results while containing only 1.53 M and 1.66 M parameters respectively on two public datasets: Inria Aerial Image Labeling Dataset and Massachusetts Buildings Dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|