Integrating Point and Line Features for Visual-Inertial Initialization

Liu, Hong; Qiu, Junyin; Huang, Weibo

doi:10.1109/icra46639.2022.9811641

Cited by 4 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The joint initialization method was first proposed by Martinelli [ 49 ], who presented a closed-form solution to jointly solve feature depth (scale), gravity, accelerometer bias, and initial velocity by linear least squares. Subsequent joint initialization methods are basically extended based on this method, including [ 50 , 51 , 52 ]. The advantage of joint initialization is that the interaction between the parameters is fully considered, and the disadvantage is that the real-time performance and the convergence of the solution process are not stable.…”

Section: Related Workmentioning

confidence: 99%

ESVIO: Event-Based Stereo Visual-Inertial Odometry

Liu

Shi

et al. 2023

Sensors

View full text Add to dashboard Cite

The emerging event cameras are bio-inspired sensors that can output pixel-level brightness changes at extremely high rates, and event-based visual-inertial odometry (VIO) is widely studied and used in autonomous robots. In this paper, we propose an event-based stereo VIO system, namely ESVIO. Firstly, we present a novel direct event-based VIO method, which fuses events’ depth, Time-Surface images, and pre-integrated inertial measurement to estimate the camera motion and inertial measurement unit (IMU) biases in a sliding window non-linear optimization framework, effectively improving the state estimation accuracy and robustness. Secondly, we design an event-inertia semi-joint initialization method, through two steps of event-only initialization and event-inertia initial optimization, to rapidly and accurately solve the initialization parameters of the VIO system, thereby further improving the state estimation accuracy. Based on these two methods, we implement the ESVIO system and evaluate the effectiveness and robustness of ESVIO on various public datasets. The experimental results show that ESVIO achieves good performance in both accuracy and robustness when compared with other state-of-the-art event-based VIO and stereo visual odometry (VO) systems, and, at the same time, with no compromise to real-time performance.

show abstract

Section: Related Workmentioning

confidence: 99%

ESVIO: Event-Based Stereo Visual-Inertial Odometry

Liu

Shi

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…As a result, researchers have started exploring trajectory-based methods (Kothari et al, 2021 ) and considered visual-inertial initialization (Huang et al, 2021 ; Liu et al, 2022 ) to address crowd avoidance problems. Nevertheless, trajectory-based approaches suffer from high computational costs, inability to perform real-time updates in the presence of increasing crowd sizes and difficulties in finding safe paths (Trautman and Krause, 2010 ; Alahi et al, 2016 ; Sathyamoorthy et al, 2020 ).…”

Section: Related Workmentioning

confidence: 99%

SafeCrowdNav: safety evaluation of robot crowd navigation in complex scenes

Xu,

Zhang,

Cai

et al. 2023

Front. Neurorobot.

Self Cite

View full text Add to dashboard Cite

Navigating safely and efficiently in dense crowds remains a challenging problem for mobile robots. The interaction mechanisms involved in collision avoidance require robots to exhibit active and foresighted behaviors while understanding the crowd dynamics. Deep reinforcement learning methods have shown superior performance compared to model-based approaches. However, existing methods lack an intuitive and quantitative safety evaluation for agents, and they may potentially trap agents in local optima during training, hindering their ability to learn optimal strategies. In addition, sparse reward problems further compound these limitations. To address these challenges, we propose SafeCrowdNav, a comprehensive crowd navigation algorithm that emphasizes obstacle avoidance in complex environments. Our approach incorporates a safety evaluation function to quantitatively assess the current safety score and an intrinsic exploration reward to balance exploration and exploitation based on scene constraints. By combining prioritized experience replay and hindsight experience replay techniques, our model effectively learns the optimal navigation policy in crowded environments. Experimental outcomes reveal that our approach enables robots to improve crowd comprehension during navigation, resulting in reduced collision probabilities and shorter navigation times compared to state-of-the-art algorithms. Our code is available at https://github.com/Janet-xujing-1216/SafeCrowdNav.

show abstract

“…As artificial intelligence technology continues to evolve, mobile robots are taking on increasingly pivotal roles across a multitude of fields (Rubio et al, 2019 ; Huang et al, 2020 ; Liu et al, 2022 ). To enable these robots to more effectively comprehend and adapt to complex, ever-changing indoor environments, it becomes essential to provide a detailed description of the scene (Johnson et al, 2016 ; Chen et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Dense captioning and multidimensional evaluations for indoor robotic scenes

Wang,

et al. 2023

Front. Neurorobot.

Self Cite

View full text Add to dashboard Cite

The field of human-computer interaction is expanding, especially within the domain of intelligent technologies. Scene understanding, which entails the generation of advanced semantic descriptions from scene content, is crucial for effective interaction. Despite its importance, it remains a significant challenge. This study introduces RGBD2Cap, an innovative method that uses RGBD images for scene semantic description. We utilize a multimodal fusion module to integrate RGB and Depth information for extracting multi-level features. And the method also incorporates target detection and region proposal network and a top-down attention LSTM network to generate semantic descriptions. The experimental data are derived from the ScanRefer indoor scene dataset, with RGB and depth images rendered from ScanNet's 3D scene serving as the model's input. The method outperforms the DenseCap network in several metrics, including BLEU, CIDEr, and METEOR. Ablation studies have confirmed the essential role of the RGBD fusion module in the method's success. Furthermore, the practical applicability of our method was verified within the AI2-THOR embodied intelligence experimental environment, showcasing its reliability.

show abstract

Integrating Point and Line Features for Visual-Inertial Initialization

Cited by 4 publications

References 22 publications

ESVIO: Event-Based Stereo Visual-Inertial Odometry

ESVIO: Event-Based Stereo Visual-Inertial Odometry

SafeCrowdNav: safety evaluation of robot crowd navigation in complex scenes

Dense captioning and multidimensional evaluations for indoor robotic scenes

Contact Info

Product

Resources

About