Lintao Zheng

Learn More
We address the problem of autonomously exploring unknown objects in a scene by consecutive depth acquisitions. The goal is to reconstruct the scene while online identifying the objects from among a large collection of 3D shapes. Fine-grained shape identification demands a meticulous series of observations attending to varying views and parts of the object(More)
Fuzzy learning algorithm of UAV is considered in this paper. It allows real time self-tuning of parameters of the controller's membership functions. The primary structure of the fuzzy controller is synthesized via &#x201C;crisp&#x201D; prototype based on the robust H<inf>2</inf>/H<inf>&#x221E;</inf>-optimization. It is shown that obtained control algorithm(More)
Multi-scale analysis has been widely used for constructing texture descriptors by modeling the coefficients in transformed domains. However, the resulting descriptors are not robust to the rotated textures when performing texture classification. To alleviate this problem, we in this paper propose a multi-scale counting and difference representation (CDR) of(More)
Over the last few decades underwater image processing has received considerable attention due to its challenging nature and its importance. The quality of underwater images is worse than that of images shot in the air and images usually appear foggy and hazy. In this paper a novel algorithm is proposed for underwater image enhancement. Our algorithm is(More)
Understanding 3D environments is a vital element of modern computer vision research due to paramount relevance in many vision systems, spanning a wide field of application scenarios from self-driving cars to autonomous robots [Qi et al. 2016]. At the present time, object recognition mainly employs two methods: volumetric CNNs [Wu Z 2015] and multi-view CNNs(More)
Missing features often occurs in both streamline placement and streamline selection. To solve this problem, a feature-based approach to streamline selection that can guarantee the preservation of the integrity of flow field features is presented in this paper. The streamline feature type is defined based on the relationship between streamlines and flow(More)
The widely used energy features extracted from the wavelet domain can effectively represent the common image textures. However, they are not robust to the rotated textures. In this letter, we propose a multiscale rotation-invariant representation (MRIR) of textures by using multiscale sampling. Particularly, a multiscale wavelet transform is used to(More)
Active vision is inherently attention-driven: The agent selects views of observation to best approach the vision task while improving its internal representation of the scene being observed. Inspired by the recent success of attentionbased models in 2D vision tasks based on single RGB images, we propose to address the multi-view depth-based active object(More)
  • 1