On Improving the Efficiency of the Technical Vision System of the Robotics Complex

One of the most important elements of the groundbased robotic complex is the vision system. Taking into account the requirements for increasing the autonomy of robotic complexes, an important function of a robotic complex is the detection and recognition of objects in the field of view. The article is devoted to solving the problem of increasing the efficiency of object recognition by the vision system due to the integration of heterogeneous information: optical and radar images. A convolutional neural network was used as a recognition device. It is shown that the integration of information makes it possible to increase the efficiency of the technical vision system of the robotic complex by 38-43%.

• Publication year

  2025

• Venue

  2025 Systems of Signals Generating and Processing in the Field of on Board Communications

• Publication date

  2025-03-12

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/IEEECONF64229.2025.10948107
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multi-Modal Fusion Sensing: A Comprehensive Review of Millimeter-Wave Radar and Its Integration With Other Modalities

  2025cited by this paper
• Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey

  2024cited by this paper
• Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges

  2023cited by this paper
• Multi-Object Detection and Tracking, Based on DNN, for Autonomous Vehicles: A Review

  2021cited by this paper
• 3D Object Detection for Autonomous Driving: A Survey

  2021cited by this paper
• Deep learning in multi-object detection and tracking: state of the art

  2021cited by this paper
• Development of the Research Stand for Exploration of Models and Algorithms for Group Control of Ground-Based Mobile Robots

  2021cited by this paper
• Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review

  2020cited by this paper
• Assessment of the Accuracy of Determining the Coordinates and Speed of Small-Size UAV of a Multi-Position Radar with Omnidirectional Antenna Elements

  2020cited by this paper
• Automotive

  2020cited by this paper
• Development of the Research Stand «Smart City Systems» INDUSTRY 4.0

  2019cited by this paper
• Deep Learning for Visual Tracking: A Comprehensive Survey

  2019cited by this paper
• Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

  2019cited by this paper
• Deep Learning for 3D Point Clouds: A Survey

  2019cited by this paper
• Automotive multi-mode cascaded radar data processing embedded system

  2018cited by this paper
• The directions for collaborate usage of flight apparatus technical vision system information and electronic cartography

  2016cited by this paper
• Collision sensing by stereo vision and radar sensor fusion

  2008cited by this paper
• Rule-based expert systems: The mycin experiments of the stanford heuristic programming project

  1985cited by this paper
• Upper and Lower Probabilities Induced by a Multivalued Mapping

  1967cited by this paper

• Radar and Camera Fusion for Improving the Efficiency of the Technical Vision System of the Ground-Based Unmanned Vehicle

  2025cites this paper