Erickson R. Nascimento

Research Projects

	Semantic Hyperlapse In this project, we deal with a central challenge that is to make egocentric videos watchable. First person videos are generally long-running streams with unedited content, which make them boring and visually unpalatable. In this project we propose a novel methodology to compose the new fast-forward video by selecting frames in a smart manner and based in the semantic information extracted from images. More information about the Semantic Hyperlapse project.
	High Performance Moves Recognition Compared with daily human gestures, moves in high performance sports are faster and have low inter-class variability, which produce noisy features and ambiguity. We present a discriminative key pose-based approach for moves recognition and segmentation of training sequences for high performance sports. Dataset and more information about high performance moves recognition.
	Efficient 3D model estimation methodology for large datasets The advent of digital cameras heralded many possibilities of structure and shape re- covery from imagery that are quickly and inexpensively acquired by such devices. In this work we propose an efficient approach based on structure from motion and multi-view stereo reconstruction techniques to automatically generate DEM - Digital Elevation Models - from aerial images and also 3D models in general.
	Image and Depth Super-Resolution With the purpose of increasing data resolution, at the same time reducing noise and filling the holes in the depth maps, in this work we propose a method that combines depth fusion and image reconstruction in a super- resolution framework. Download the conference paper (Best Computer Graphics Paper Award of SIBGRAPI 2015).
	Keypoint descriptor extraction for RGB-D data At the core of a myriad of tasks such as object recognition, tridimensional recon- struction and alignment resides the critical problem of correspondence. We introduce BRAND descriptors that efficiently combine appearance and geometrical shape information from RGB-D images, and are largely invariant to rotation, illumination changes and scale transformations. Download the journal paper.