The lab focuses on advancing research in machine learning, computer vision and big data analytics for remote sensing applications to address the state-of-the-art technical and application challenges.
Rapid advances in sensor technology, field robotics, unmanned aerial systems (UAS), and computing power have facilitated exponential growth in remote sensing applications. Meanwhile, processing complex, multiscale, and multidimensional data from UAS, environmental sensors and climate model simulations has become increasingly difficult for both scientists and public to summarize and visualize the large amount of data for agricultural and environmental assessments with direct applications to education, training and decision-making. Data generated by thousands of images collected in a single UAS flight is almost impossible to manually analyze. There exist both numerous opportunities and challenges with broader usage of multi-sensor remote sensing data, mostly attributed to processing algorithms of ultra-high resolution imagery, translating the abundant spectral and spatial data to information useful for decision-making. Machine Learning, as a multidisciplinary field, seeks to mimic human brain system for automatic extraction, analysis, and interpreting useful information from images or a sequence of video frames.
- Sidike, P., Asari, V., Sagan, V. (2018). Progressively Expanded Neural Network (PEN Net) for hyperspectral image classification: a new neural network paradigm for remote sensing image analysis. ISPRS Journal of Photogrammetry and Remote Sensing, 146: 161-181. [Link]
- Maimaitijiang, M., Ghulam, A., Sidike, P., Hartling, S., Maimaitiyiming, M., Peterson, K., Shavers, E., Peterson, J., Kadam, S., Burken, J., Fritschi, F. (2017). Unmanned aerial system-based phenotyping of soybean using multi-sensor data fusion and extreme learning machine. ISPRS Journal of Photogrammetry and Remote Sensing, 134:43-58. [Link]
- Peterson, K.T., Sagan, V., Sidike, P., Cox, A.L., Martinez, M. (2018). Suspended sediment concentration estimation from Landsat imagery along the lower Missouri and middle Mississippi Rivers using extreme learning machine. Remote Sens., 10(10), 1503. [Link]
- Sidike, P., Sagan, V., Maimaitijiang, M., Maimaitiyiming, M., Shakoor, N., Burken, J., Mockler, T., Fritschi, F. (2018). dPEN: deep Progressively Expanded Network for mapping of heterogeneous agricultural landscape using WorldView-3 imagery. Remote Sensing of Environment. (major revision).
- Maimaitiyiming, M., Sagan, V., Sidike, P., Kwasniewski, M. (2018). Improved Extreme Learning Machine (ELM) for estimating grapevine berry yield and quality under different irrigation treatments and rootstocks conditions. ISPRS Journal of Photogrammetry and Remote Sensing. (major revision).
- Peterson, K.T., Sagan, V., Sidike, P., Hasenmueller, E., Sloan, J., Knouft, J. (2018). Machine learning based ensemble prediction of water quality variables with proximal remote sensing using feature-level and decision-level fusion. Photogrammetric Engineering and Remote Sensing, Sept. 2018. (in press).
- Albalooshi, F., Sidike, P., Sagan, V., Albastaki Y., and Asari, V. (2018). Deep Belief Active Contours (DBAC) with Its Application to Oil Spill Segmentation from Remotely Sensed Aerial Imagery. Photogrammetric Engineering and Remote Sensing, 84(7): 451-458. [Link]
- Sidike, P., Ghulam, A., Asari, V.K., and Alam, M.S. (2017). Efficient hyperspectral target detection using class-associative spectral fringe-adjusted JTC with dimensionality reduction techniques, Asian Journal of Physics, 26(3&4): 171:180.
- Sean Hartling, Sagan, V., Sidike, P., et al. (2018). Machine learning based forest tree species mapping using Worldview-3 and airborne LiDAR data fusion. (in submission).
- Sidike, P., Sagan, V., et al. (2018). Deep learning based plant density estimation: application to durum wheat and soybean. (in submission).