AI Products / Services > Professional Service

ZIA™ SAFE Safety Driving Assistance Development

header image

Overview

Professional service, enabling to develop an advanced safe driving support system in a short period of time.

Specific Implementing Function Examples

Out-of-vehicle Camera

  • Forward vehicle collision detection, rear vehicle collision detection, side vehicle collision detection
  • Forward start delay detection
  • Traffic light ignoring detection
    • Traffic light location and color detection
  • Stop sign ignoring detection
    • Object detection of road signs (railroad crossings, stop lines, stop signs, etc.)
  • Stop detection at stop line
  • Road sign detection (various road signs can be detected by learning images)
  • License plate recognition and mosaic processing
  • Face mosaic
  • Road Structure Recognition by Segmentation Analysis
    • Target road structures are own lanes, sidewalks, roads, fences, poles, dividers, etc.
    • Judgment whether to contact road structure from the positional relationship between the wall and own lane

In-vehicle Camera

  • Driver monitoring (DMS function) by recognizing in-vehicle camera image
  • Drowsy driving detection
  • Face orientation detection (inattentive driving)
  • Smartphone (mobile phone) detection
  • Hand position detection by detecting the skeleton of the arm (determining whether drivers have an object in their hand or not, distracted driving detection)

* Whether or not function support is possible depends on the hardware specifications and performance that the customer adopts, so discussions and considerations are necessary in each case.

Implementation Steps

Customer's product development process
1. Suvery and Planning
  • By introducing DMP's mobility technology and interviewing customer's purposes of using AI, clarify what customers want to achieve by using AI and proposes the best way to proceed
2. PoC Development
  • After clarifying the purposes of AI utilization, collect actual data from customers, or collect and create necessary data, and perform annotations, selection of the optimal combination of ZIA™ SAFE building blocks, and evaluation and tuning of learning and accuracy
  • Usually use CPU, GPU, or FPGA as the hardware platform for PoC development
3. System Development
  • If the AI utilization effects can be expected in the PoC development, perform development to implement AI model in the actual target system
  • Optimize and implement the AI model is according to customer's requirement of performance and power and the hardware platform (CPU, GPU, FPGA, etc.) to be used
  • DMP's strength is to be able to offer technology from reducing the weight of AI models to optimizing GPUs, DSPs, and AI accelerators used by hardware platforms, or logic designing for SoC / FPGA for hardware acceleration.
4. Utilization
  • Offer periodic re-training and optimization since the accuracy of the AI model changes due to changes in the external environment (changes in usage conditions, etc.)
  • Optimize the AI model according to changes in the customer's target platform

Related News

expand_less