All Outputs (25)

Weakly supervised deep semantic segmentation using CNN and ELM with semantic candidate regions. (2019)
Journal Article
XU, X., LI, G., XIE, G., REN, J. and XIE, X. 2019. Weakly supervised deep semantic segmentation using CNN and ELM with semantic candidate regions. Complexity [online], 2019: complex deep learning and evolutionary computing models in computer vision, article 9180391. Available from: https://doi.org/10.1155/2019/9180391

The task of semantic segmentation is to obtain strong pixel-level annotations for each pixel in the image. For fully supervised semantic segmentation, the task is achieved by a segmentation model trained using pixel-level annotations. However, the pi... Read More about Weakly supervised deep semantic segmentation using CNN and ELM with semantic candidate regions..

Fault detection of a spherical tank using a genetic algorithm-based hybrid feature pool and k-nearest neighbor algorithm. (2019)
Journal Article
HASAN, M.J. and KIM, J.-M. 2019. Fault detection of a spherical tank using a genetic algorithm-based hybrid feature pool and k-nearest neighbor algorithm. Energies [online], 12(6): fault diagnosis and fault-tolerant control, article 991. Available from: https://doi.org/10.3390/en12060991

Fault detection in metallic structures requires a detailed and discriminative feature pool creation mechanism to develop an effective condition monitoring system. Traditional fault detection methods incorporate handcrafted features either from the ti... Read More about Fault detection of a spherical tank using a genetic algorithm-based hybrid feature pool and k-nearest neighbor algorithm..

Superpixel based feature specific sparse representation for spectral-spatial classification of hyperspectral images. (2019)
Journal Article
SUN, H., REN, J., ZHAO, H., YAN, Y., ZABALZA, J. and MARSHALL, S. 2019. Superpixel based feature specific sparse representation for spectral-spatial classification of hyperspectral images. Remote sensing [online], 11(5), article 536. Available from: https://doi.org/10.3390/rs11050536

To improve the performance of the sparse representation classification (SRC), we propose a superpixel-based feature specific sparse representation framework (SPFS-SRC) for spectral-spatial classification of hyperspectral images (HSI) at superpixel le... Read More about Superpixel based feature specific sparse representation for spectral-spatial classification of hyperspectral images..

Video for pick&place study in AFRC project. [Dataset] (2019)
Dataset
YAN, Y., ZABALZA, J., MINEO, C., YANG, E., FEI, Z. and WANG, C. 2019. Video for pick&place study in AFRC project. [Dataset]. Hosted on Pureportal (University Strathclyde) [online]. Available from: https://doi.org/10.15129/4df22803-2cc4-4cce-9cea-509f88f1b504

In order to extend the abilities of current robots in industrial applications towards more autonomous and flexible manufacturing, this work presents an integrated system comprising real-time sensing, path-planning and control of industrial robots to... Read More about Video for pick&place study in AFRC project. [Dataset].

FinSeg: finger parts semantic segmentation using multi-scale feature maps aggregation of FCN. (2019)
Conference Proceeding
SALEH, A., RASHWAN, H., ABDEL-NASSER, M., SINGH, V., ABDULWAHAB, S., SARKER, M., GARCIA, M. and PUIG, D. 2019. FinSeg: finger parts semantic segmentation using multi-scale feature maps aggregation of FCN. In Tremeau, A., Farinella, G.M. and Braz, J. (eds.). Proceedings of 14th international joint conferences on Computer vision, imaging and computer graphics theory and applications 2019 (VISIGRAPP 2019), 25-27 February 2019, Prague, Czech Republic. Setúbal, Portugal: SciTePress [online], 5, pages 77-84. Available from: https://doi.org/10.5220/0007382100770084

Image semantic segmentation is in the center of interest for computer vision researchers. Indeed, huge number of applications requires efficient segmentation performance, such as activity recognition, navigation, and human body parsing, etc. One of t... Read More about FinSeg: finger parts semantic segmentation using multi-scale feature maps aggregation of FCN..