Eric Smith

Eric Smith

Principal Engineer

Eric Smith joined Kitware in 2011 and is a Principal Engineer on the Computer Vision Team. He holds a Ph.D. in computer vision from Rensselaer Polytechnic Institute, where he also received his B.S. in computer science. 

Dr. Smith’s research at Kitware has largely focused on image enhancement and 3D reconstruction. He is currently leading image enhancement projects for both underwater (DARPA) and overhead (NGA) domains. He is a key contributor to Kitware’s 3D reconstruction application, Telesculptor. Dr. Smith recently led an effort on aerial 3D reconstruction (AFRL) contributing depth map estimation and fusion to Telesculptor. His recent research at Kitware has included deep learning for estimating depth maps, super-resolution, modality transfer, semantic segmentation, and object detection. He has previously worked on variational algorithms for both dense depth estimation and super-resolution from video, as well as camera trajectory tracking of an endoscope.

Dr. Smith’s graduate research focused on the automatic registration of combined image/LiDAR scans. He developed a pairwise registration algorithm designed to handle scan pairs suffering from low overlap, changes, intensity differences, and wide viewpoint differences. Dr. Smith has also worked on feature detection, description, and matching algorithms targeted at coarse alignment for combined image/LiDAR scans. He has also developed a fully automatic multiple scan registration algorithm using both pairwise and graph-based validation methods.

  1. M. Leotta, E. Smith, and D. Russell, "TeleSculptor: Dense 3D Models from Uncalibrated FMV," in Proceedings of the MSS National Symposium on Passive Sensors, 2018.
  2. C. Long, E. Smith, A. Basharat, and A. Hoogs, "A C3D-based convolutional neural network for frame dropping detection in a single video shot," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop on Media Forensics, 2017. [URL]
  3. J. Moeller, E. Smith, A. Basharat, M. Turek, A. Hoogs, and E. Blasch, "Automatic pattern of life learning in satellite images through graph kernels," in Proceedings of the MSS National Symposium on Sensor and Data Fusion, 2017.
  4. M. Leotta, E. Smith, M. Dawkins, and P. Tunison, "Open source structure-from-motion for aerial video," in Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2016. [URL]
  5. M. Leotta, P. Tunison, E. Smith, and M. Dawkins, "MAP-Tk: Motion imagery Aerial Photogrammetry Toolkit," in Proceedings of the MSS National Symposium on Passive Sensors, 2015.
  6. E. Smith, R. Radke, and C. Stewart, "Physical Scale Keypoints: Matching and Registration for Combined Intensity/Range Images," International Journal of Computer Vision, vol. 97, no. 1, pp. 2-17, Mar. 2012. [URL]
  7. E. Smith, "Registration of combined range-intensity scans," Ph.D. dissertation, Rensselaer Polytechnic Institute, 2012.
  8. E. R Smith, R. Radke, and C. Stewart, "Physical Scale Intensity-Based Range Keypoints," in Proceedings of the International Symposium on 3D Data Processing, Visualization, and Transmission, 2010.
  9. E. Smith, B. King, C. Stewart, and R. Radke, "Registration of combined range–intensity scans: Initialization through verification," Computer Vision and Image Understanding, vol. 110, no. 2, pp. 226-244, May 2008. [URL]

Bibliography generated 2019-12-02-07:30:10 (3301)