Pixel-Level Matching for Video Object Segmentation using Convolutional Neural Networks
| Autor: | Seunghak Shin, Junsik Kim, In So Kweon, Seokju Lee, Francois Rameau, Jae Shin Yoon |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
Similarity (geometry) Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Feature extraction Representation (systemics) Computer Science - Computer Vision and Pattern Recognition 020207 software engineering Pattern recognition 02 engineering and technology Object (computer science) Convolutional neural network Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence business |
| Zdroj: | ICCV |
| Popis: | We propose a novel video object segmentation algorithm based on pixel-level matching using Convolutional Neural Networks (CNN). Our network aims to distinguish the target area from the background on the basis of the pixel-level similarity between two object units. The proposed network represents a target object using features from different depth layers in order to take advantage of both the spatial details and the category-level semantic information. Furthermore, we propose a feature compression technique that drastically reduces the memory requirements while maintaining the capability of feature representation. Two-stage training (pre-training and fine-tuning) allows our network to handle any target object regardless of its category (even if the object's type does not belong to the pre-training data) or of variations in its appearance through a video sequence. Experiments on large datasets demonstrate the effectiveness of our model - against related methods - in terms of accuracy, speed, and stability. Finally, we introduce the transferability of our network to different domains, such as the infrared data domain. To appear on ICCV 2017 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|