Abstract
Visual object recognition plays an important role in the fields of computer vision and robotics. Static analysis of an image from a single viewpoint may not contain enough information to recognize an object unambiguously. Active object recognition (AOR) is aimed at collecting additional information to reduce ambiguity by purposefully adjusting the viewpoint of an observer. Existing AOR methods are oriented to a single task whose goal is to recognize an object by the minimum number of viewpoints. This paper presents a novel framework to deal with multiple AOR tasks based on feature decision tree (FDT). In the framework, in the light of the distribution of predetermined features on each object in a model base, a prior feature distribution table is firstly created as a kind of prior knowledge. Then it is utilized for the construction of FDT which describes the transition process of recognition states when different viewpoints are selected. Finally, in order to determine the next best viewpoints for the tasks with different goals, a unified optimization problem is established and solved by tree dynamic programming algorithm. In addition, the existing evaluation method of viewpoint planning (VP) efficiency is improved. According to whether the prior probability of the appearance of each object is known, the VP efficiency of different tasks is evaluated respectively. Experiments on the simulation and real environment show that the proposed framework obtains rather promising results in different AOR tasks.
Similar content being viewed by others
References
Kasaei, S.H., Oliveira, M., Lim, G.H., Seabra Lopes, L., Tomé, A.M.: Interactive open-ended learning for 3D object recognition: an approach and experiments. J. Intell. Robot. Syst. 80, 537–553 (2015)
Han, X., Liu, H., Sun, F., Zhang, X.: Active object detection with multi-step action prediction using deep Q-network. IEEE Trans. Ind. Inform. 15(6), 3723–3731 (2019)
Aloimonos, J., Weiss, I.: Active vision. Int. J. Comput. Vis. 1(4), 333–356 (1988)
Bajcsy, R.: Active perception. Proc. IEEE. 76(8), 966–1005 (1988)
Thermos, S., Papadopoulos, G.T., Daras, P., Potamianos, G.: Deep sensorimotor learning for RGB-D object recognition. Comput. Vis. Image Underst. 190, 102844 (2020)
Liu, M., Shi, Y., Zheng, L., Xu, K., Huang, H., Manocha, D.: Recurrent 3D attentional networks for end-to-end active object recognition. Comput.Vis. Media. 5(1), 91–104 (2019)
Liu, H., Wu, Y., Sun, F.: Extreme trust region policy optimization for active object recognition. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2253–2258 (2018)
Gallos, D., Ferrie, F.: Active Vision in the Era of Convolutional Neural Networks. Proceedings of the 16th Conference on Computer and Robot Vision, pp. 81–88 (2019)
Zeng, R., Wen, Y., Zhao, W., Liu, Y. J.: View planning in robot active vision: A survey of systems, algorithms, and applications. Comput.Vis. Media. pp. 1–21(2020)
Zeng, R., Wen, Y., Zhao, W., Liu, Y.J.: Active vision in robotic systems: a survey of recent developments. Int. J. Robot. Res. 30(11), 1343–1377 (2011)
Andreopoulos, A., Tsotsos, J.K.: 50 years of object recognition: directions forward. Comput. Vis. Image Underst. 117(8), 827–891 (2013)
Gremban, K.D., Ikeuchi, K.: Planning multiple observations for object recognition. Int. J. Comput. Vis. 12(2–3), 137–172 (1994)
Roy, S.D., Chaudhury, S., Banerjee, S.: Isolated 3D object recognition through next view planning. IEEE Trans. Syst. Man Cybern. -Syst. 30(1), 67–76 (2000)
Dickinson, S.J., Christensen, H.I., Tsotsos, J.K., Olofsson, G.: Active object recognition integrating attention and viewpoint control. Comput. Vis. Image Underst. 67(3), 239–260 (1997)
Schiele, B., Crowley, J. L.: Transinformation for Active Object Recognition. Proceedings of the IEEE International Conference on Computer Vision. pp. 249–254 (1988)
Ye, Y., Tsotsos, J.K.: Sensor planning for 3D object search. Comput. Vis. Image Underst. 73(2), 145–168 (1999)
Borotschnig, H., Paletta, L., Prantl, M., Pinz, A.: Appearance-based active object recognition. Image Vis. Comput. 18(9), 715–727 (2000)
Callari, F.G., Ferrie, F.P.: Active object recognition: looking for differences. Int. J. Comput. 43(3), 189–204 (2001)
Denzler, J., Brown, C.M.: Information theoretic sensor data selection for active object recognition and state estimation. IEEE Trans. Pattern Anal. Mach. Intell. 24(2), 145–157 (2002)
Laporte, C., Arbel, T.: Efficient discriminant viewpoint selection for active bayesian recognition. Int. J. Comput. 68(3), 267–287 (2006)
Browatzki, B., Tikhanoff, V., Metta, G., Bülthoff, H.H., Wallraven, C.: Active in-hand object recognition on a humanoid robot. Proceedings of the IEEE International Conference on robotics and automation. pp. 2021-2028, (2012)
Browatzki, B., Tikhanoff, V., Metta, G., Bülthoff, H.H., Wallraven, C.: Active object recognition on a humanoid robot. IEEE Trans. Robot. 30(5), 1260–1269 (2014)
Wu, K., Ranasinghe, R., Dissanayake, G.: Active recognition and pose estimation of household objects in clutter. Proceedings of the IEEE International Conference on Robotics and Automation. pp. 4230–4237 (2015)
Imperoli, M., Pretto, A.: Active detection and localization of textureless objects in cluttered environments. In Proc. CVIU, pp. 1–18 (2016)
Potthast, C., Breitenmoser, A., Sha, F., Sukhatme, G.S.: Active multi-view object recognition: a unifying view on online feature selection and view planning. Robot. Auton. Syst. 84, 31–47 (2016)
Patten, T., Zillich, M., Fitch, R., Vincze, M., Sukkarieh, S.: Viewpoint evaluation for online 3-D active object classification. IEEE Robot. Autom. Lett. 1(1), 73–81 (2015)
Paletta, L., Pinz, A.: Active object recognition by view integration and reinforcement learning. Robot. Auton. Syst. 31(1–2), 71–86 (2000)
Deinzer, F., Denzler, J., Derichs, C., Niemann, H.: Aspects of optimal viewpoint selection and viewpoint fusion. In Asian Conference on Computer Vision, pp. 902–912 (2006)
Malmir, M., Sikka, K., Forster, D., Movellan, J. R., Cottrell, G.: Deep Q-learning for active recognition of germs: Baseline performance on a standardized dataset for active learning. Proceedings of the BMVC, pp. 161.1–161.11 (2015)
Liu, H., Li, F., Xu, X., Sun, F.: Active object recognition using hierarchical local-receptive-field-based extreme learning machine. Memet. Comput. 10(2), 233–241 (2017)
Sun, H., Zhu, F., Hao, Y., Fu, S., Kong Y., Xu, C.: Active object recognition based on prior feature distribution table. 2020 3rd International Conference on Unmanned Systems (ICUS), pp. 1012–1017 (2020)
Code Availability
Code generated or used during the study is available from the corresponding author by request.
Funding
This work is supported by the National Natural Science Foundation of China under Grant no. U1713216.
Author information
Authors and Affiliations
Contributions
Haibo Sun, Feng Zhu and Yingming Hao conceived and designed the approach. Yanzi Kong strongly contributed in the construction of simulation and real experimental environment. Shuangfei Fu helped with code implementation, data collection, and experimentation. The first draft of the manuscript was written by Haibo Sun. Chenglong Xu and Jianyu Wang thoroughly corrected the manuscript. All authors read and approved the final manuscript.
Corresponding authors
Ethics declarations
Ethics Approval
Not applicable.
Consent to Participate
Not applicable.
Consent for Publication
Not applicable.
Conflict of Interest
All the authors of this paper have no conflicts of interest, financial or otherwise.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sun, H., Zhu, F., Hao, Y. et al. Unified Optimization for Multiple Active Object Recognition Tasks with Feature Decision Tree. J Intell Robot Syst 103, 31 (2021). https://doi.org/10.1007/s10846-021-01488-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10846-021-01488-x