389 skills found · Page 3 of 13
lambdaloop / Checkerboard🏁 More robust checkerboard detection, similar algorithm to libcbdetect
BTREE-C802 / 3DLine SLAM3DLines-SLAM: A Monocular Vision Semi-Dense 3D Reconstruction Based on ORB-SLAM Abstract-Producing high-quality 3D maps and calculating more accurate camera pose has always been the goal of SLAM technology. The requirements of SLAM technology such as real-time, low computational cost, and low hardware cost are contradictory to the above objectives. For the issues listed above, we propose a novel semi-dense reconstruction algorithm based on the monocular ORB-SLAM system by matching the line segment features extracted from keyframes. Specifically, we build upon ORB-SLAM, the system first provides a set of keyframes and their corresponding camera poses and a series of map points in real-time. Then we use our developed a keyframe re-culling algorithm to culling redundant keyframes. Then an improved line segment extraction method is used to extract line segments in each keyframe. Finally, we use purely geometric constraints to generates accurate 3D scene model by matching 2D line segments from different keyframes. We thoroughly evaluate and in-depth analysis of our approach, the results show our system runs steadily and reliably. Not only the whole system has strong robustness, but also it can quickly generate an accurate 3d model online with low computational costs.
krishnap25 / RFARobust aggregation for federated learning with the RFA algorithm.
LokiResearch / Fast Triangle Triangle IntersectionFast and robust triangle-triangle intersection test with high precision for cross and coplanar triangles based on the algorithm by Devillers & Guigue.
numericalEFT / MCIntegration.jlRobust and fast Monte Carlo algorithm for high dimension integration
HFTHaidra / Deep Reinforcement Learning For Automated Stock Trading StrategyStock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose a deep ensemble reinforcement learning scheme that automatically learns a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using the three actor-critic based algorithms: Proximal Policy Optimization (PPO), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG). The ensemble strategy inherits and integrates the best features of the three algorithms, thereby robustly adjusting to different market conditions. In order to avoid the large memory consumption in training networks with continuous action space, we employ a load-on-demand approach for processing very large data. We test our algorithms on the 30 Dow Jones stocks which have adequate liquidity. The performance of the trading agent with different reinforcement learning algorithms is evaluated and compared with both the Dow Jones Industrial Average index and the traditional min-variance portfolio allocation strategy. The proposed deep ensemble scheme is shown to outperform the three individual algorithms and the two baselines in terms of the risk-adjusted return measured by the Sharpe ratio.
ZhaoyangLyu / POPQORNAn Algorithm to Quantify Robustness of Recurrent Neural Networks
amirallami-code / Binary Search AlgorithmThis repository houses a robust implementation of the binary search algorithm. Binary search is a highly efficient method for locating an item in a sorted list by systematically dividing the search interval in half.
yuanxy92 / AutoWhiteBalanceefficient and robust white balance algorithm
dgaspari / PyraptA pitch tracker inspired by David Talkin's RAPT (Robust Algorithm for Pitch Tracking) written in Python.
julianmer / DA MUSIC TVT23Extensions of DA-MUSIC handle broadband signals and varying numbers of sources, improving accuracy and robustness over the original MUSIC algorithm.
matthew-gaddes / ICASARAn algorithm for robustly appling sICA to InSAR data
ricedsp / PrDeepThis package contains the code to run prDeep; a noise robust phase retrieval algorithm based on deep neural networks.
chs74515 / PeopleCounterIn present days, people detection, tracking and counting is an important aspect in the video investigation and subjection demand in Computer Vision Systems. Providing (real time) traffic information will help improve and reduce pedestrian and vehicle traffic, especially when the data collected is learned and analyzed over a period of time, which makes its highly essential to identify people, vehicles and objects in general and also accurately counting the number of people and/or vehicles entering and leaving a particular location in real time. To perform people counting, a robust and efficient system is needed. This research is aimed at making a pedestrian traffic reporting system for certain areas and buildings around the campus to potentially help ease traffic circulation. Providing this information will be done through a developed application, which includes image processing with Open Computer Vision (OpenCV). This will show the amount of traffic in certain buildings or area over a period of time. OpenCV is a cross-platform library which can be used to develop real-time Computer Vision applications [Opencv, 2015b]. It is mainly focused on image processing, video capture and analysis including features like people and object detection. The operations performed were based on the performance and accuracy of the tracking algorithms when implemented in embedded devices such as the Raspberry Pi and the Tinker Board. The Pi Camera was used for real time vision and hosted on the embedded device. The proposed method used was conjoined with an open-source visual tracking implementation from the contribution branch of the OpenCV library and a unique technique for people detection along with different Filtering Algorithms for tracking this. The programming language of choice to implement these features (Tracking and Detection) is python and its libraries. The present work describes a standalone people counting application designed using Python OpenCV and tested on embedded devices ranging from the Raspberry Pi3 to a Tinker Board and a compatible Camera. All these were used in prototyping the design of this application. The results reported and showed that the Person-Counter system developed counted the number of people entering the designated area (down), and the number of people leaving (up).
aidos-lab / TARDISTARDIS: Topological Algorithms for Robust DIscovery of Singularities
Geng-Hao / Robust Model Free Iterative Learning Control With Convergence Rate AccelerationA novel model-free iterative learning control algorithm is presented in this project to improve both the robustness against output disturbances and the tracking performance in steady-state. For model-free ILC, several methods have been investigated, such as the time- reversal error filtering, the Model-Free Inversion-based Iterative Control (MFIIC), and the Non- Linear Inversion-based Iterative Control (NLIIC). However, the time-reversal error filtering has a conservative learning rate. Other two methods, although with much faster error convergence, have either a high noise sensitivity or a non-optimized steady-state. To improve the performance and robustness of model-free ILC, in this project we apply the time-reversal based ILC algorithm and recursively accelerate its error convergence using the online identified learning filter. The effectiveness of the proposed algorithm has been validated from a numerical simulation. The proposed approach not only improves the transient response of the MFIIC, but also achieves lower tracking error in steady-state compared to that of the NLIIC.
leosocy / RobustPalmRoiA robust algorithm for extracting ROI from palm image taken by mobile phone.
facebookresearch / Pitfalls Of MemorizationUnderstanding the interplay between memorization and generalization in neural networks, featuring MAT, a learning algorithm to enhance robustness by mitigating spurious correlations.
XinyiYS / Robust And Fair Federated LearningImplementing the algorithm from our paper: "A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning".
sellali360 / LPVThis algorithm exhibits a robust Energy Management Strategy (EMS) for battery-super capacitor (SC) Hybrid Energy Storage System (HESS). The proposed algorithm, dedicated to an electric vehicular application, it is based on a self-gain scheduled controller, which guarantees the H performance for a class of linear parameter varying (LPV) systems.
