Related papers: Efficient Implementation of a Recognition System U…
Composite convex optimization models arise in several applications, and are especially prevalent in inverse problems with a sparsity inducing norm and in general convex optimization with simple constraints. The most widely used algorithms…
All kinds of simulations of the intergalactic medium, such as hydrodynamic simulation, N-body simulation, numerical and semi-numerical simulation, etc., have been used to realize the history of this medium. In addition, emulators also have…
Advancements in AI have greatly enhanced the medical imaging process, making it quicker to diagnose patients. However, very few have investigated the optimization of a multi-model system with hardware acceleration. As specialized edge…
A system for live high quality surface reconstruction using a single moving depth camera on a commodity hardware is presented. High accuracy and real-time frame rate is achieved by utilizing graphics hardware computing capabilities via…
Low level images representation in feature space performs poorly for classification with high accuracy since this level of representation is not able to project images into the discriminative feature space. In this work, we propose an…
This paper proposes a representational model for image pairs such as consecutive video frames that are related by local pixel displacements, in the hope that the model may shed light on motion perception in primary visual cortex (V1). The…
Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to…
Contrast maximization (CMAX) is a direct geometric framework for event-based motion estimation, but its iterative warp-and-accumulate pipeline incurs input-dependent computation and frequent memory accesses, challenging real-time, low-power…
We present a new wrapper feature selection algorithm for human detection. This algorithm is a hybrid feature selection approach combining the benefits of filter and wrapper methods. It allows the selection of an optimal feature vector that…
For scalable autonomous driving, a robust map-based localization system, independent of GPS, is fundamental. To achieve such map-based localization, online high-definition (HD) map construction plays a significant role in accurate…
In this paper, an efficient near-field beamforming method is proposed to support the large intelligent surfaces (LIS) that are expected to be widely deployed in 6G networks. This approach avoids directly applying convex (CVX) optimization…
A well-designed fine-grained categorization system usually has three contradictory requirements: accuracy (the ability to identify objects among subordinate categories); interpretability (the ability to provide human-understandable…
Object detection algorithms for Lidar data have seen numerous publications in recent years, reporting good results on dataset benchmarks oriented towards automotive requirements. Nevertheless, many of these are not deployable to embedded…
Deep convolutional neural networks achieve remarkable visual recognition performance, at the cost of high computational complexity. In this paper, we have a new design of efficient convolutional layers based on three schemes. The 3D…
The homography matrix is a key component in various vision-based robotic tasks. Traditionally, homography estimation algorithms are classified into feature- or intensity-based. The main advantages of the latter are their versatility,…
Hybrid vision transformers combine the elements of conventional neural networks (NN) and vision transformers (ViT) to enable lightweight and accurate detection. However, several challenges remain for their efficient deployment on…
Hierarchical Matrix (H-matrix) is an approximation technique which splits a target dense matrix into multiple submatrices, and where a selected portion of submatrices are low-rank approximated. The technique substantially reduces both time…
This paper tackles the problem of real-time semantic segmentation of high definition videos using a hybrid GPU / CPU approach. We propose an Efficient Video Segmentation(EVS) pipeline that combines: (i) On the CPU, a very fast optical flow…
This paper aims at developing an automatic algorithm for moth recognition from trap images in real-world conditions. This method uses our previous work for detection [1] and introduces an adapted classification step. More precisely, SVM…
Underwater image enhancement has become an attractive topic as a significant technology in marine engineering and aquatic robotics. However, the limited number of datasets and imperfect hand-crafted ground truth weaken its robustness to…