Loading...
12 results
Search Results
Now showing 1 - 10 of 12
- 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.
- 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.
- 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 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.
- Multi-scale cortical keypoints for realtime hand tracking and gesture recognitionPublication . Farrajota, Miguel; Saleiro, Mário; Terzic, Kasim; Rodrigues, J. M. F.; du Buf, J. M. H.Human-robot interaction is an interdisciplinary research area which aims at integrating human factors, cognitive psychology and robot technology. The ultimate goal is the development of social robots. These robots are expected to work in human environments, and to understand behavior of persons through gestures and body movements. In this paper we present a biological and realtime framework for detecting and tracking hands. This framework is based on keypoints extracted from cortical V1 end-stopped cells. Detected keypoints and the cells’ responses are used to classify the junction type. By combining annotated keypoints in a hierarchical, multi-scale tree structure, moving and deformable hands can be segregated, their movements can be obtained, and they can be tracked over time. By using hand templates with keypoints at only two scales, a hand’s gestures can be recognized.
- Phase-differencing in stereo vision: solving the localisation problemPublication . du Buf, J. M. H.; Terzic, Kasim; Rodrigues, J. M. F.Complex Gabor filters with phases in quadrature are often used to model even- and odd-symmetric simple cells in the primary visual cortex. In stereo vision, the phase difference between the responses of the left and right views can be used to construct a disparity or depth map. Various constraints can be applied in order to construct smooth maps, but this leads to very imprecise depth transitions. In this theoretical paper we show, by using lines and edges as image primitives, the origin of the localisation problem. We also argue that disparity should be attributed to lines and edges, rather than trying to construct a 3D surface map in cortical area V1. We derive allowable translation ranges which yield correct disparity estimates, both for left-view centered vision and for cyclopean vision.
- 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.
- 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.
- Real-Time Object Recognition Based on Cortical Multi-scale KeypointsPublication . Terzic, Kasim; Rodrigues, J. M. F.; du Buf, J. M. H.In recent years, a large number of impressive object categorisation algorithms have surfaced, both computational and biologically motivated. While results on standardised benchmarks are impressive, very few of the best-performing algorithms took run-time performance into account, rendering most of them useless for real-time active vision scenarios such as cognitive robots. In this paper, we combine cortical keypoints based on primate area V1 with a state-of-the-art nearest neighbour classifier, and show that such a system can approach state-of-the-art categorisation performance while meeting the real-time constraint.
- 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.