We introduce an efficient, robust means of obtaining reliable surface descriptions, suitable for object recognition, at multiple scales from range data. Mean and Gaussian curvatures are used to segment the surface into regions of four saliency classes, each based on curvature consistency. We evaluate curvature consistency in a robust multivoting scheme. Contiguous regions consistent in both mea...

We propose an interferometric scheme based on an untrapped nano-object subjected to gravity. The motion of the center of mass (c.m.) of the free object is coupled to its internal spin system magnetically, and a free flight scheme is developed based on coherent spin control. The wave packet of the test object, under a spin-dependent force, may then be delocalized to a macroscopic scale. A gravit...

Instance segmentation has attracted recent attention in computer vision and existing methods in this domain mostly have an object detection stage. In this paper, we study the intrinsic challenge of the instance segmentation problem, the presence of a quotient space (swapping the labels of different instances leads to the same result), and propose new methods that are object proposaland object d...

Many fiber-fed spectroscopic survey projects, such as DESI, PFS and MOONS, will use thousands of fiber positioners packed at a focal plane. To maximize observation time, the positioners need to move simultaneously and reach their targets swiftly. We have previously presented a motion planning method based on a decentralized navigation function for the collision-free coordination of the fiber po...

The recognition of free-form 3-D objects using multi-scale features recovered from 3-D models, and based on the geometric hashing algorithm and global veri cation is presented. The feature points on the object are detected by smoothing its surface after construction of semigeodesic coordinates at each point (mesh vertex). This technique is the generalisation of the CSS method which is a powerfu...

Advances in computer speed, memory capacity, and hardware graphics acceleration have made the interactive manipulation and visualization of complex, detailed (and therefore large) three-dimensional models feasible. These models are either painstakingly designed through an elaborate CAD process or reverse engineered from sculpted prototypes using modern scanning technologies and integration meth...

This paper presents a new approach to free-form object modeling from multiple range images. In most conventional approaches, successive views are registered sequentially. In contrast to the sequential approaches, we propose an integral approach which reconstructs statistically optimal object models by simultaneously aggregating all data from multiple views into a weighted least-squares (WLS) fo...

In this paper we present an approach to estimate Free Space from a Stereo image pair using stochastic occupancy grids. We do this in the domain of autonomous driving on the famous benchmark dataset KITTI. Later based on the generated occupancy grid we match 2 image sequences to compute the top view representation of the map. We do this to map the environment. We compute a transformation between...

Pointers are ubiquitous in modern object-oriented programming languages, and many data structures such as trees, lists, graphs, hash tables, etc. depend on them heavily. Unfortunately, pointers can add significant complexity to programming. ParaSail, a new parallel object-oriented programming language, has adopted an alternative, pointer-free approach to defining data structures. Rather than us...

The increasing use of virtual object representations for several applications creates a need for fast and simple object digitizing systems. Range finders provide a convenient way to digitize solid objects and permit the accurate and fast scanning of an object shape without any probe contact. However, only one view of an object can be captured at once and therefore for most objects several views...