Core Technologies

Based on the foundation of proprietary technologies and a core “brain” built on a deep learning platform, SenseTime has rapidly opened up AI application in multiple vertical scenarios.

Autonomous Driving

Autonomous Driving

Technical Capabilities

Pedestrian, Motor Vehicle and Non-Motor Vehicle Detection
Vehicle Movement and Attribute Analysis
Pedestrian Behavior and Attribute Analysis
Lane Detection
Scene Understanding
Traffic Light and Traffic Sign Recognition
High-PrecisionReal-Time Positioning of Large-Scale Scenes
High-Precision 3D Reconstruction of Large-Scale Scenes
Path Planning and Decision Control
FPGA Platform-Based Model Deployment

Pedestrian, Motor Vehicle and Non-Motor Vehicle Detection

The system accurately and promptly recognizes pedestrians, motor vehicles, and non-motor vehicles in various complex road environments.

Vehicle Movement and Attribute Analysis

The system provides accurate analysis of the attributes and characteristics of vehicles in the scene, including motion status, direction, trajectory, and light signals of the vehicles.

Pedestrian Behavior and Attribute Analysis

The system accurately recognizes attributes and characteristics of pedestrians in the scene, including movements and body orientations of the pedestrians.

Lane Detection

The system recognizes attributes of different roads and lanes under different environmental conditions in an accurate and fast manner.

Scene Understanding

The system supports accurate and fast perception of the scenes for pixel-level semiotic symbols so as to achieve scene modelling.

Traffic Light and Traffic Sign Recognition

The system supports accurate and fast recognition of traffic signs and lights in complex road environments and understanding their meanings.

High-PrecisionReal-Time Positioning of Large-Scale Scenes

The system leverages mainly visual information and integrates multiple low-cost sensor solutions to achieve highly accurate real-time positioning in large-scale urban scenes.

High-Precision 3D Reconstruction of Large-Scale Scenes

The system achieves 3D geometric reconstruction and texture mapping for large-scale urban scenes with assistance of multi-perspective cameras, radars, satellite positioning, and inertial navigation systems to provide high-quality 3D map data for autonomous driving.

Path Planning and Decision Control

The system leverages accurate sensor results to make rational and logical decisions in driving route planning and vehicle control.

FPGA Platform-Based Model Deployment

Fast deployment of neural networks on FPGA platform with efficient model compression and acceleration technology to achieve highly flexible, low-cost autonomous driving technology.