In this paper we have addressed the implementation of the accumulation and projection of high-resolution event data stream (HD – 1280×720 pixels) onto the image plane in FPGA devices. The results confirm the fea...
In this paper we have addressed the implementation of the accumulation and projection of high-resolution event data stream (HD – 1280×720 pixels) onto the image plane in FPGA devices. The results confirm the feasibility of this approach, but there are a number of challenges, limitations and trade-offs to be considered. The required hardware resources of selected data representations, such as binary frame, event frame, exponentially decaying time surface and event frequency, were compared with those available on several popular platforms from AMD Xilinx. The resulting event frames can be used for typical vision algorithms, such as object classification and detection, using both classical and deep neural network methods.
In this paper we have addressed the implementation of the accumulation and projection of high-resolution event data stream (HD – 1280 × 720 pixels) onto the image plane in FPGA devices. The results confirm the f...
详细信息
In this work, we numerically compare accuracy and robustness of five popular phase retrieval approaches for lensless digital holographic microscopy. In our analysis we consider three single-frame approaches: (1) semin...
详细信息
Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To addre...
详细信息
Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To addre...
Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To address these challenges, one can check the effectiveness of different models by training on a subset of the original training set. In this paper, we present a comparison of three algorithms for selecting such a subset – random sampling, random per class sampling, and our proposed MONSPeC (Maximum Object Number Sampling per Class). We provide empirical evidence for the superior effectiveness of random per class sampling and MONSPeC over basic random sampling. By replacing random sampling with one of the more efficient algorithms, the results obtained on the subset are more likely to transfer to the results on the entire dataset. The code is available at: https://***/vision-agh/monspec.
Object detection and segmentation are two core modules of an autonomous vehicle perception system. They should have high efficiency and low latency while reducing computational complexity. Currently, the most commonly...
Object detection and segmentation are two core modules of an autonomous vehicle perception system. They should have high efficiency and low latency while reducing computational complexity. Currently, the most commonly used algorithms are based on deep neural networks, which guarantee high efficiency but require high-performance computing platforms. In the case of autonomous vehicles, i.e. cars, but also drones, it is necessary to use embedded platforms with limited computing power, which makes it difficult to meet the requirements described above. A reduction in the complexity of the network can be achieved by using an appropriate: architecture, representation (reduced numerical precision, quantisation, pruning), and computing platform. In this paper, we focus on the first factor – the use of so-called detection-segmentation networks as a component of a perception system. We considered the task of segmenting the drivable area and road markings in combination with the detection of selected objects (pedestrians, traffic lights, and obstacles). We compared the performance of three different architectures described in the literature: MultiTask V3, HybridNets, and YOLOP. We conducted the experiments on a custom dataset consisting of approximately 500 images of the drivable area and lane markings, and 250 images of detected objects. Of the three methods analysed, MultiTask V3 proved to be the best, achieving 99% mAP 50 for detection, 97% MIoU for drivable area segmentation, and 91% MIoU for lane segmentation, as well as 124 fps on the RTX 3060 graphics card. This architecture is a good solution for embedded perception systems for autonomous vehicles. The code is available at: https://***/vision-agh/MMAR_2023.
Object detection in 3D is a crucial aspect in the context of autonomous vehicles and drones. However, prototyping detection algorithms is time-consuming and costly in terms of energy and environmental impact. To addre...
详细信息
robotics and haptic systems have allowed new and diverse applications in the field of medicine, such as assisted surgery and teleoperation which have increasingly stringent requirements for accuracy, convergence, and ...
详细信息
ISBN:
(数字)9798350393965
ISBN:
(纸本)9798350393972
robotics and haptic systems have allowed new and diverse applications in the field of medicine, such as assisted surgery and teleoperation which have increasingly stringent requirements for accuracy, convergence, and low computational consumption. In this paper an adaptive PID control law (Proportional Integral Derivative controller, PID), of indirect architecture is presented for movement paths in a haptic system of open chain, where the identification of the plant is through a quaternionic wavelet neural network (Quaternion Wavelet Neural Network, QWNN) for tune the PID values, this allows the optimal movement into the regions of the workspace.
Artificial Neural Networks (ANNs) have shown great potential in enhancing Human-Robot Interaction (HRI). ANNs are computational models inspired by the structure and function of biological neural networks in the brain,...
详细信息
In this work, we present the modeling of the dynamics of a robot manipulator using the Newton-Euler algorithm in the conformal algebra framework. The modeling of the dynamics of robot manipulators is currently done us...
详细信息
ISBN:
(数字)9798350362343
ISBN:
(纸本)9798350362350
In this work, we present the modeling of the dynamics of a robot manipulator using the Newton-Euler algorithm in the conformal algebra framework. The modeling of the dynamics of robot manipulators is currently done using the Euler-Lagrange formulation which is a batch type of computation. In contrast, in this paper, we propose a recursive algorithm for the modeling of the dynamics of robot manipulators using the Newton-Euler algorithm in the conformal geometric algebra framework.
暂无评论