Fx26h superpixel program

Such the hybrid U-Net can exploit features of HSIs from a multi-scale hierarchical perspective, and its performance has been proved competitive with other deep-learning-based methods by extensive experiments on three benchmark data sets. Skip to content. Star MIT License. Branches Tags. Could not load branches. Could not load tags. Latest commit. Git stats 16 commits. The proposed methodology contains two main steps. In suspicious fire region proposal, we introduce a novel superpixel algorithm SCMM driven by Cauchy mixture model.

Then, the negative Under-segmentation Error UE of each superpixel is applied to inter-frame comparison for predicting varying superpixels.

After that, by computing the features of motion superpixels using Local Difference Binary LDB descriptor for two adjacent frames, the suspicious fire regions are localized. In following fire identification, to improve network performance while reducing computational complexity, this study presents a light-weight network architecture, called Expanded Squeeze-and-Excitation ShuffleNet ESE-ShuffleNet.

All suspicious fire regions are sent into this network to identify as either fire or non-fire included. Experiments show that our framework performs well on fire detection tasks. This is a preview of subscription content, access via your institution. Rent this article via DeepDyve.

Article Google Scholar. Dunnings AJ, Breckon TP Experimentally defined convolutional neural network architecture variants for non-temporal real-time fire detection. Foggia P, Saggese A, Vento M Real-time fire detection for video-surveillance applications using a combination of experts based on color, shape, and motion. Huo, L. Itti, L. Jiang, H. In: British Machine Vision Conference Kadir, T. Liu, T. Ma, Y. Ojala, T. Otsu, N. Ren, C. Computer Science Rother, C. Shi, J. Wang, J. Vision 2 , — Wei, Y.

Yan, Q. Yang, C. Yildirim, G. Springer, Berlin Like the superpixel program, it uses some of the code in the WatershedWithClosingOpenPumpkinsBetter-m file i order to split the pumpkin clusters.

The Functionclass. The AnalysisClass. The BlockProcessFunc. The blockprocessTest. Skip to content.