Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation

Alam, Fahim Irfan; Zhou, Jun; Liew, Alan Wee-Chung; Jia, Xiuping; Chanussot, Jocelyn; Gao, Yongsheng

doi:10.48550/arxiv.1711.04483

Cited by 2 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperspectral imaging plays an important role in remote sensing as it provides hundreds of contiguous, narrow spectral bands [1]. With the advantage of rich spectral information, hyperspectral images (HSIs) have been widely used in many applications involving image classification [2] and segmentation [3], such as land cover detection and mining. However, to the best of our knowledge, there is very little work focusing on hyperspectral video processing.…”

Section: Introductionmentioning

confidence: 99%

Object Tracking in Hyperspectral Videos with Convolutional Features and Kernelized Correlation Filter

Qian

Zhou

Xiong

et al. 2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Target tracking in hyperspectral videos is a new research topic. In this paper, a novel method based on convolutional network and Kernelized Correlation Filter (KCF) framework is presented for tracking objects of interest in hyperspectral videos. We extract a set of normalized three-dimensional cubes from the target region as fixed convolution filters which contain spectral information surrounding a target. The feature maps generated by convolutional operations are combined to form a three-dimensional representation of an object, thereby providing effective encoding of local spectral-spatial information. We show that a simple two-layer convolutional networks is sufficient to learn robust representations without the need of offline training with a large dataset. In the tracking step, KCF is adopted to distinguish targets from neighboring environment. Experimental results demonstrate that the proposed method performs well on sample hyperspectral videos, and outperforms several state-of-the-art methods tested on grayscale and color videos in the same scene.

show abstract

Section: Introductionmentioning

confidence: 99%