No abstract

This paper presents Space-Time Occupancy Patterns (STOP), a new visual representation for 3D action recognition from sequences of depth maps. In this new representation, space and time axes are divided into multiple segments to define a 4D grid for each depth map sequence. The advantage of STOP is that it preserves spatial and temporal contextual information between space-time cells while being flexible enough to accommodate intra-action variations. Our visual representation is validated with experiments on a public 3D human action dataset. For the challenging cross-subject test, we significantly improved the recognition accuracy from the previously reported 74.7% to 84.8%. Furthermore, we present an automatic segmentation and time alignment method for online recognition of depth sequences.

No abstract

No abstract

This work introduces a novel descriptor called Binary Robust Appearance and Normals Descriptor (BRAND), that efficiently combines appearance and geometric shape information from RGB-D images, and is largely invariant to rotation and scale transform. The proposed approach encodes point information as a binary string providing a descriptor that is suitable for applications that demand speed performance and low memory consumption. Results of several experiments demonstrate that as far as precision and robustness are con cerned, BRAND achieves improved results when compared to state of the art descriptors based on texture, geometry and combination of both information. We also demonstrate that our descriptor is robust and provides reliable results in a registration task even when a sparsely textured and poorly illuminated scene is used.

No abstract

Melanins have been associated with the development of melanoma and its resistance to photodynamic therapy (PDT). Singlet molecular oxygen ((1)O(2)), which is produced by ultraviolet A solar radiation and the PDT system, is also involved. Here, we investigated the effects that these factors have on DNA damage and repair. Our results show that both types of melanin (eumelanin and pheomelanin) lead to DNA breakage in the absence of light irradiation and that eumelanin is more harmful than pheomelanin. Interestingly, melanins were found to bind to the minor grooves of DNA, guaranteeing close proximity to DNA and potentially causing the observed high levels of strand breaks. We also show that the interaction of melanins with DNA can impair the access of repair enzymes to lesions, contributing to the perpetuation of DNA damage. Moreover, we found that after melanins interact with (1)O(2), they exhibit a lower ability to induce DNA breakage; we propose that these effects are due to modifications of their structure. Together, our data highlight the different modes of action of the two types of melanin. Our results may have profound implications for cellular redox homeostasis, under conditions of induced melanin synthesis and irradiation with solar light. These results may also be applied to the development of protocols to sensitize melanoma cells to PDT.

The objective of this work was to propose an automated and direct process to grade tooth wear intra-orally. Eight extracted teeth were etched with acid for different times to produce wear and scanned with an intra-oral optical scanner. Computer vision algorithms were used for alignment and comparison among models. Wear volume was estimated and visual scoring was achieved to determine reliability. Results demonstrated that it is possible to directly detect submillimeter differences in teeth surfaces with an automated method with results similar to those obtained by direct visual inspection. The investigated method proved to be reliable for comparison of measurements over time.