Browsing by Author "Terzic, Kasim"
Now showing 1 - 10 of 14
Results Per Page
Sort Options
- A fast neural-dynamical approach to scale-invariant object detectionPublication . Terzic, Kasim; Lobato, D.; Saleiro, Mário; du Buf, J. M. H.We present a biologically-inspired method for object detection which is capable of online and one-shot learning of object appearance. We use a computationally efficient model of V1 keypoints to select object parts with the highest information content and model their surroundings by a simple binary descriptor based on responses of cortical cells. We feed these features into a dynamical neural network which binds compatible features together by employing a Bayesian criterion and a set of previously observed object views. We demonstrate the feasibility of our algorithm for cognitive robotic scenarios by evaluating detection performance on a dataset of common household items. © Springer International Publishing Switzerland 2014.
- A parametric spectral model for texture-based saliencePublication . Terzic, Kasim; Krishna, Sai; du Buf, J. M. H.; Gall, J.; Gehler, P.; Leibe, B.We present a novel saliency mechanism based on texture. Local texture at each pixel is characterised by the 2D spectrum obtained from oriented Gabor filters. We then apply a parametric model and describe the texture at each pixel by a combination of two 1D Gaussian approximations. This results in a simple model which consists of only four parameters. These four parameters are then used as feature channels and standard Difference-of-Gaussian blob detection is applied in order to detect salient areas in the image, similar to the Itti and Koch model. Finally, a diffusion process is used to sharpen the resulting regions. Evaluation on a large saliency dataset shows a significant improvement of our method over the baseline Itti and Koch model.
- BIMP: A real-time biological model of multi-scale keypoint detection in V1Publication . Terzic, Kasim; Rodrigues, J. M. F.; du Buf, J. M. H.We present an improved, biologically inspired and multiscale keypoint operator. Models of single- and double-stopped hypercomplex cells in area V1 of the mammalian visual cortex are used to detect stable points of high complexity at multiple scales. Keypoints represent line and edge crossings, junctions and terminations at fine scales, and blobs at coarse scales. They are detected by applying first and second derivatives to responses of complex cells in combination with two inhibition schemes to suppress responses along lines and edges. A number of optimisations make our new algorithm much faster than previous biologically inspired models, achieving real-time performance on modern GPUs and competitive speeds on CPUs. In this paper we show that the keypoints exhibit state-of-the-art repeatability in standardised benchmarks, often yielding best-in-class performance. This makes them interesting both in biological models and as a useful detector in practice. We also show that keypoints can be used as a data selection step, significantly reducing the complexity in state-of-the-art object categorisation. (C) 2014 Elsevier B.V. All rights reserved.
- BINK: Biological binary keypoint descriptorPublication . Saleiro Filho, Mario; Terzic, Kasim; Rodrigues, João; du Buf, J. M. H.Learning robust keypoint descriptors has become an active research area in the past decade. Matching local features is not only important for computational applications, but may also play an important role in early biological vision for disparity and motion processing. Although there were already some floatingpoint descriptors like SIFT and SURF that can yield high matching rates, the need for better and faster descriptors for real-time applications and embedded devices with low computational power led to the development of binary descriptors, which are usually much faster to compute and to match. Most of these descriptors are based on purely computational methods. The few descriptors that take some inspiration from biological systems are still lagging behind in terms of performance. In this paper, we propose a new biologically inspired binary keypoint descriptor: SINK. Built on responses of cortical V1 cells, it significantly outperforms the other biologically inspired descriptors. The new descriptor can be easily integrated with a V1-based keypoint detector that we previously developed for real-time applications. (C) 2017 Elsevier B.V. All rights reserved.
- A biological and real-time framework for hand gestures and head posesPublication . Saleiro, Mário; Farrajota, Miguel; Terzic, Kasim; Rodrigues, J. M. F.; du Buf, J. M. H.Human-robot interaction is an interdisciplinary research area that aims at the development of social robots. Since social robots are expected to interact with humans and understand their behavior through gestures and body movements, cognitive psychology and robot technology must be integrated. In this paper we present a biological and real-time framework for detecting and tracking hands and heads. This framework is based on keypoints extracted by means of cortical V1 end-stopped cells. Detected keypoints and the cells’ responses are used to classify the junction type. Through the combination of annotated keypoints in a hierarchical, multi-scale tree structure, moving and deformable hands can be segregated and tracked over time. By using hand templates with lines and edges at only a few scales, a hand’s gestures can be recognized. Head tracking and pose detection are also implemented, which can be integrated with detection of facial expressions in the future. Through the combinations of head poses and hand gestures a large number of commands can be given to a robot.
- Biological models for active vision: towards a unified architecturePublication . Terzic, Kasim; Lobato, D.; Saleiro, Mário; Martins, Jaime; Farrajota, Miguel; Rodrigues, J. M. F.; du Buf, J. M. H.Building a general-purpose, real-time active vision system completely based on biological models is a great challenge. We apply a number of biologically plausible algorithms which address different aspects of vision, such as edge and keypoint detection, feature extraction,optical flow and disparity, shape detection, object recognition and scene modelling into a complete system. We present some of the experiments from our ongoing work, where our system leverages a combination of algorithms to solve complex tasks.
- Biologically Inspired Vision for Indoor Robot NavigationPublication . Saleiro, Mário; Terzic, Kasim; Lobato, D.; Rodrigues, J. M. F.; du Buf, J. M. H.Ultrasonic, infrared, laser and other sensors are being applied in robotics. Although combinations of these have allowed robots to navigate, they are only suited for specific scenarios, depending on their limitations. Recent advances in computer vision are turning cameras into useful low-cost sensors that can operate in most types of environments. Cameras enable robots to detect obstacles, recognize objects, obtain visual odometry, detect and recognize people and gestures, among other possibilities. In this paper we present a completely biologically inspired vision system for robot navigation. It comprises stereo vision for obstacle detection, and object recognition for landmark-based navigation. We employ a novel keypoint descriptor which codes responses of cortical complex cells. We also present a biologically inspired saliency component, based on disparity and colour.
- A disparity energy model improved by line, edge and keypoint correspondencesPublication . Martins, J. C.; Farrajota, Miguel; Lam, Roberto; Rodrigues, J. M. F.; Terzic, Kasim; du Buf, J. M. H.Disparity energy models (DEMs) estimate local depth information on the basis ofVl complex cells. Our recent DEM (Martins et al, 2011 ISSPlT261-266) employs a population code. Once the population's cells have been trained with randorn-dot stereograms, it is applied at all retinotopic positions in the visual field. Despite producing good results in textured regions, the model needs to be made more precise, especially at depth transitions.
- Fast and accurate multi-scale keypoints based on end-stopped cellsPublication . Terzic, Kasim; Rodrigues, J. M. F.; du Buf, J. M. H.Increasingly more applications in computer vision employ interest points. Algorithms like SIFT and SURF are all based on partial derivatives of images smoothed with Gaussian filter kemels. These algorithrns are fast and therefore very popular.
- Fast cortical keypoints for real-time object recognitionPublication . Terzic, Kasim; Rodrigues, J. M. F.; du Buf, J. M. H.Best-performing object recognition algorithms employ a large number features extracted on a dense grid, so they are too slow for real-time and active vision. In this paper we present a fast cortical keypoint detector for extracting meaningful points from images. It is competitive with state-of-the-art detectors and particularly well-suited for tasks such as object recognition. We show that by using these points we can achieve state-of-the-art categorization results in a fraction of the time required by competing algorithms.