Back-end optimization plays a key role in eliminating the accumulated error in Visual Simultaneous Localization And Mapping (VSLAM). Existing back-end optimization methods are usually premised on the Gaussian noise assumption which does not always hold true due to the non-convex nature of the image and the fact that non-Gaussian noises are often encountered in real scenes. In view of this, we propose a back-end optimization method based on Multi-Convex combined Maximum Correntropy Criterion (MCMCC). A MCMCC-based cost function is first tailored for nonlinear back-end optimization in the context of VSLAM and the optimization problem is solved through Levenberg-Marquardt algorithm iteratively. Then, the proposed method is applied to ORB-SLAM3 to test its performance on public indoor and outdoor datasets. The real time performance is also validated using a RaceBot platform in real indoor and outdoor environments. In addition, the reprojection error is statistically analyzed to demonstrate the non-Gaussian characteristics in the back-end optimization process. Finally, the suggestion parameters are also provided through experiments for further study.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.isatra.2023.08.006 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Cation composition ratio and channel length effects on bias stress instability in amorphous InGaZnO back-end-of-line field-effect transistors.
Sci Rep
December 2024
School of Electrical Engineering, Kookmin University, Seoul, 02707, Republic of Korea.
This study optimizes V and ΔV in amorphous indium-gallium-zinc-oxide (a-IGZO) field-effect transistors (FETs) by examining the influence of both channel length (L) and Ga composition. It was observed that as the ratio of In: Ga: Zn changed from 1:1:1 to 0.307:0.
View Article and Find Full Text PDFInnovative Ultralow Thermal Budget ZrHfOx Ferroelectric Films with Low-Temperature Phase Transition for Next-Generation High-Speed Multifunctional Devices.
Nano Lett
January 2025
School of Microelectronics, State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai 200433, P. R. China.
By design of the element concentration, regulating the ratio of the t phase and the energy difference between t and o phases, the ZrHfOx (ZHO) film demonstrated the highest polarization value at a maximum processing temperature of only 280 °C without an annealing process, and it can withstand over 10 polarization cycles without breakdown. The ZHO film maintains good ferroelectric performance in extreme temperature environments (4.55 to 473 K).
View Article and Find Full Text PDFSec-CLOCs: Multimodal Back-End Fusion-Based Object Detection Algorithm in Snowy Scenes.
Sensors (Basel)
November 2024
School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China.
LiDAR and cameras, often regarded as the "eyes" of intelligent driving vehicles, are vulnerable to adverse weather conditions like haze, rain, and snow, compromising driving safety. In order to solve this problem and enhance the environmental sensing capability under severe weather conditions, this paper proposes a multimodal back-end fusion object detection method, Sec-CLOCs, which is specifically optimized for vehicle detection under heavy snow. This method achieves object detection by integrating an improved YOLOv8s 2D detector with a SECOND 3D detector.
View Article and Find Full Text PDFResearch on Visual-Inertial Measurement Unit Fusion Simultaneous Localization and Mapping Algorithm for Complex Terrain in Open-Pit Mines.
Sensors (Basel)
November 2024
School of Mechanical and Automotive Engineering, Guangxi University of Science and Technology, Liuzhou 545006, China.
As mining technology advances, intelligent robots in open-pit mining require precise localization and digital maps. Nonetheless, significant pitch variations, uneven highways, and rocky surfaces with minimal texture present substantial challenges to the precision of feature extraction and positioning in traditional visual SLAM systems, owing to the intricate terrain features of open-pit mines. This study proposes an improved SLAM technique that integrates visual and Inertial Measurement Unit (IMU) data to address these challenges.
View Article and Find Full Text PDFTraditional full-Stokes polarization imaging typically relies on the movements or segmentation of imaging systems, often accompanied by sacrifices in temporal or spatial resolution. Therefore, simultaneous encoding of full-Stokes vectors at the pixel scale is of great significance. Benefiting from the multi-dimensional light field control capability of metasurfaces, a coded aperture metasurface for polarization imaging is proposed in this paper, which can achieve pixel-level encoding of four Stokes vectors in a single imaging session.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!