检索结果-内蒙古大学图书馆

2011 IEEE International Conference on robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)

作者： Dominik A. Klein Armin B. Cremers Intelligent Vision Systems Group Department of Computer Science IIIRheinische Friedrich-Wilhelms-Universit(a)t Bonn53117 BonnGermany

Recently, several image gradient and edge based features have been introduced. In unison, they all discovered that object shape is a strong cue for recognition and tracking. Generally their basic feature extraction relies on pixel-wise gradient or edge computation using discrete filter masks, while scale invariance is later achieved by higher level operations like accumulating histograms or abstracting edgels to line segments. In this paper we show a novel and fast way to compute region based gradient features which are scale invariant themselves. We developed specialized, quick learnable weak classifiers that are integrated into our adaptively boosted observation model for particle filter based tracking. With an ensemble of region based gradient features this observation model is able to reliably capture the shape of the tracked object. The observation model is adapted to new object and background appearances while tracking. Thus we developed advanced methods to decide when to update the model, or in other words, if the filter is on target or not. We evaluated our approach using the BoBoT1 as well as the PROST2 datasets.

关键词： Adaptation models Target tracking Computational modeling Shape Training Reliability Real time systems

来源：评论

学校读者我要写书评

暂无评论

One deep music representation to rule them all? A comparative analysis of different representation learning strategies

arXiv

引用

arXiv 2018年

作者： Kim, Jaehun Urbano, Julián Liem, Cynthia C.S. Hanjalic, Alan Multimedia Computing Group Department of Intelligent Systems Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology

Inspired by the success of deploying deep learning in the fields of computer vision and Natural Language Processing, this learning paradigm has also found its way into the field of Music Information Retrieval. In order to benefit from deep learning in an effective, but also efficient manner, deep transfer learning has become a common approach. In this approach, it is possible to reuse the output of a pre-trained neural network as the basis for a new learning task. The underlying hypothesis is that if the initial and new learning tasks show commonalities and are applied to the same type of input data (e.g. music audio), the generated deep representation of the data is also informative for the new task. Since, however, most of the networks used to generate deep representations are trained using a single initial learning source, their representation is unlikely to be informative for all possible future tasks. In this paper, we present the results of our investigation of what are the most important factors to generate deep representations for the data and learning tasks in the music domain. We conducted this investigation via an extensive empirical study that involves multiple learning sources, as well as multiple deep learning architectures with varying levels of information sharing between sources, in order to learn music representations. We then validate these representations considering multiple target datasets for evaluation. The results of our experiments yield several insights on how to approach the design of methods for learning widely deployable deep data representations in the music domain. Copyright © 2018, The Authors. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Clustering of Motion Trajectories by a Distance Measure Based on Semantic Features

Clustering of Motion Trajectories by a Distance Measure Base...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Christoph Zelch Jan Peters Oskar von Stryk Department of Computer Science TU Darmstadt Hochschulstr. 10 Simulation Systems Optimization and Robotics Group Darmstadt Germany Department of Computer Science TU Darmstadt Hochschulstr. 10 Intelligent Autonomous Systems Group Darmstadt Germany

Clustering of motion trajectories is highly relevant for human-robot interactions as it allows the anticipation of human motions, fast reaction to those, as well as the recognition of explicit gestures. Further, it allows automated analysis of recorded motion data. Many clustering algorithms for trajectories build upon distance metrics that are based on pointwise Euclidean distances. However, our work indicates that focusing on salient characteristics is often sufficient. We present a novel distance measure for motion plans consisting of state and control trajectories that is based on a compressed representation built from their main features. This approach allows a flexible choice of feature classes relevant to the respective task. The distance measure is used in agglomerative hierarchical clustering. We compare our method with the widely used dynamic time warping algorithm on test sets of motion plans for the Furuta pendulum and the Manutec robot arm and on real-world data from a human motion dataset. The proposed method demonstrates slight advantages in clustering and strong advantages in runtime, especially for long trajectories.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast-moving object counting with an event camera

arXiv

引用

arXiv 2022年

作者： Bialik, Kamil Kowalczyk, Marcin Blachut, Krzysztof Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Al. Mickiewicza 30 Krakow30-059 Poland

This paper proposes the use of an event camera as a component of a vision system that enables counting of fast-moving objects – in this case, falling corn grains. These type of cameras transmit information about the change in brightness of individual pixels and are characterised by low latency, no motion blur, correct operation in different lighting conditions, as well as very low power consumption. The proposed counting algorithm processes events in real time. The operation of the solution was demonstrated on a stand consisting of a chute with a vibrating feeder, which allowed the number of grains falling to be adjusted. The objective of the control system with a PID controller was to maintain a constant average number of falling objects. The proposed solution was subjected to a series of tests to determine the correctness of the developed method operation. On their basis, the validity of using an event camera to count small, fast-moving objects and the associated wide range of potential industrial applications can be confirmed. © 2022, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

LiDAR-based drone navigation with reinforcement learning

TechRxiv

引用

TechRxiv 2023年

作者： Miera, Pawel Szolc, Hubert Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Al. Mickiewicza 30 Krakow30-059 Poland

Reinforcement learning is of increasing importance in the field of robot control and simulation plays a key role in this process. In the unmanned aerial vehicles (UAVs, drones), there is also an increase in the number of published scientific papers involving this approach. In this work, an autonomous drone control system was prepared to fly forward (according to its coordinates system) and pass the trees encountered in the forest based on the data from a rotating LiDAR sensor. The Proximal Policy Optimization (PPO) algorithm, an example of reinforcement learning (RL), was used to prepare it. A custom simulator in the Python language was developed for this purpose. The Gazebo environment, integrated with the Robot Operating System (ROS), was also used to test the resulting control algorithm. Finally, the prepared solution was implemented in the Nvidia Jetson Nano eGPU and verified in the real tests scenarios. During them, the drone successfully completed the set task and was able to repeatably avoid trees and fly through the forest. © 2023, CC BY.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

PointPillars Backbone Type Selection For Fast and Accurate LiDAR Object Detection

TechRxiv

引用

TechRxiv 2022年

作者： Lis, Konrad Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Al. Mickiewicza 30 Krakow30-059 Poland

3D object detection from LiDAR sensor data is an important topic in the context of autonomous cars and drones. In this paper, we present the results of experiments on the impact of backbone selection of a deep convolutional neural network on detection accuracy and computation speed. We chose the PointPillars network, which is characterised by a simple architecture, high speed, and modularity that allows for easy expansion. During the experiments, we paid particular attention to the change in detection efficiency (measured by the mAP metric) and the total number of multiply-addition operations needed to process one point cloud. We tested 10 different convolutional neural network architectures that are widely used in image-based detection problems. For a backbone like MobilenetV1, we obtained an almost 4x speedup at the cost of a 1.13% decrease in mAP. On the other hand, for CSPDarknet we got an acceleration of more than 1.5x at an increase in mAP of 0.33%. We have thus demonstrated that it is possible to significantly speed up a 3D object detector in LiDAR point clouds with a small decrease in detection efficiency. This result can be used when PointPillars or similar algorithms are implemented in embedded systems, including SoC FPGAs. The code is available at https://***/vision-agh/pointpillars backbone. © 2022, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Signal propagation in transformers: theoretical perspectives and the role of rank collapse 22

Signal propagation in transformers: theoretical perspectives...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Lorenzo Noci Sotiris Anagnostidis Luca Biggio Antonio Orvieto Sidak Pal Singh Aurelien Lucchi Dept of Computer Science ETH Zürich Dept of Computer Science ETH Zürich and Robotics & ML CSEM SA Alpnach Switzerland Dept of Computer Science ETH Zürich and MPI for Intelligent Systems Tübingen Department of Mathematics and Computer Science University of Basel

ISBN: (纸本)9781713871088

Transformers have achieved remarkable success in several domains, ranging from natural language processing to computer vision. Nevertheless, it has been recently shown that stacking self-attention layers — the distinctive architectural component of Transformers — can result in rank collapse of the tokens' representations at initialization. The question of if and how rank collapse affects training is still largely unanswered, and its investigation is necessary for a more comprehensive understanding of this architecture. In this work, we shed new light on the causes and the effects of this phenomenon. First, we show that rank collapse of the tokens' representations hinders training by causing the gradients of the queries and keys to vanish at initialization. Furthermore, we provide a thorough description of the origin of rank collapse and discuss how to prevent it via an appropriate depth-dependent scaling of the residual branches. Finally, our analysis unveils that specific architectural hyperparameters affect the gradients of queries and values differently, leading to disproportionate gradient norms. This suggests an explanation for the widespread use of adaptive methods for Transformers' optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LiDAR-based drone navigation with reinforcement learning

arXiv

引用

arXiv 2023年