Traditionally, vision systems are open-loop sequential operations, which function with constant predefined parameters and have no interconnections between them. This approach has impact on the final 3D reconstruction result, since each operation in the chain is applied sequentially, with no information between the different levels of processing. In other words, low level image processing is performed regardless of the requirements of high level processing. In such a system, for example, if the segmentation module fails to provide a good output, all the subsequent steps will fail.
The basic diagram from which feedback mechanisms for machine vision are derived can be seen in the above figure. In such a control system, the control signal u, or actuator variable, is a parameter of an image processing operation, whereas the controlled, or state, variable y is a measure of processing quality.
L. Marina, B. Trasnea, C. Tiberiu, A. Vasilcoi, F. Moldoveanu and S.M. Grigorescu, “Deep Grid Net (DGN): A Deep Learning System for Real-Time Driving Context Understanding”, Int. Conf. on Robotic Computing IRC 2019, Naples, Italy, February 25-27, 2019.
B. Trasnea, L. Marina, A. Vasilcoi, C. Pozna and S.M. Grigorescu, “GridSim: A Vehicle Kinematics Engine for Deep Neuroevolutionary Control in Autonomous Driving”, Int. Conf. on Robotic Computing IRC 2019, Naples, Italy, February 25-27, 2019.
S.M. Grigorescu "Generative One-Shot Learning (GOL): A Semi-Parametric Approach to One-Shot Learning in Autonomous Vision", Int. Conf. on Robotics and Automation ICRA 2018, Brisbane, Australia, May 21-25, 2018.
S.M. Grigorescu M. Glaab and A. Roßbach "From logistic regression to self-driving cars: Chances and challenges of using machine learning for highly automated driving", Elektrobit Automotive TechPaper, 2017.
G. Macesanu, F. Moldoveanu and S.M. Grigorescu "A Time-Delay Control Approach for a Stereo Vision Based Human-Machine Interaction System", Journal of Intelligent and Robotic Systems, Springer, 2013.
S.M. Grigorescu and C. Pozna "Towards a Stable Robotic Object Manipulation through 2D-3D Features Tracking", International Journal of Advanced Robotic Systems, InTech, vol. 10, no. 200, pp. 1-8, 2013.
S.M. Grigorescu, D. Pangercic and M. Beetz "2D-3D Collaborative Tracking (23CT): Towards Stable Robotic Manipulation", Proceedings of the 2012 IEEE-RSJ International Conference on Intelligent RObots and Systems IROS, Workshop on Active Semantic Perception, Vilamoura, Algarve, Portugal, October 7-12, 2012.
S.M. Grigorescu, G. Macesanu, C. Tiberiu and F. Moldoveanu "Stereo Vision-based 3D Camera Pose and Object Structure Estimation: An Application to Service Robotics", Proceedings of the International Conference on Computer Vision Theory and Applications, Rome, Italy, February 24 - 26, 2012.
Grigorescu, S.M., Ristic-Durrant, D., Vupalla, S.K. Graeser, A. "Closed-Loop Control in Image Processing for Improvement of Object Recognition", Proceedings of the 17th IFAC World Congress, Seoul, Korea, July 06-11, ISBN: 978-3-902661-00-5, DOI: 10.3182/20080706-5-KR-1001.2132, 2008.