ADAS safety driving assistance system
ADAS (Advanced Driver Assistant System) is an active safety technology that can use AI algorithms to perform intelligent image analysis. Use various sensors installed on the car to collect environmental data inside and outside the car at the first time, and perform technical processing such as identification, detection and tracking of static and dynamic objects, so that the driver can detect potential dangers in the shortest time , Prevent the occurrence of traffic accidents. In the early days, ADAS systems were dominated by passive alarms, but now with the advancement of technology, ADAS systems have reached the level that they can actively carry out a series of safety protection operations for car owners, and further protect the safety of car owners.
The main functions of the ADAS system: vehicle collision alarm, lane departure alarm, country approaching alarm, pedestrian collision alarm, blind spot detection alarm, etc.
Recommended program: LQ3399PRO
Feature description:
1. The LQ3399PRO core board uses Rockchip's flagship chip RK3399 Pro, which uses a large and small core CPU architecture, dual-core Cortex-A72 + quad-core Cortex-A53. Built-in NPU computing unit, with 3.0TOPS computing power, supports 8bit and 16bit operations, supports typical deep neural network Inception V3, ResNet34, VGG16 and other models.
2. It can withstand a wide voltage input of -40V~60V and a working voltage range of 9V~36V, over-voltage and under-voltage protection, over-current and over-temperature protection, ignition load dump protection, etc., which can be directly connected to various types In the 12V or 24V battery power supply system, it provides a safety basis for various vehicle artificial intelligence application scenarios;
3. Multi-channel camera support
The AI solution that can be connected to 5 channels of AHD high-definition cameras or multi-channel USB depth cameras provides hardware guarantee for various application scenarios;
4. Rich functional peripherals
Integrated 4G, GPS/BD dual-mode positioning, 2.4G/5G dual-band WIFI, BT5.0 Bluetooth, 9-axis motion tracking sensor, which can meet application development in various types of scenarios, and provide evaluation and display of new products and applications The fastest prototype basis.
5. The LQ3399Pro vision host is positioned at the edge computing device terminal under the AI scene. It has rich hardware interfaces and powerful video capture functions.
specification |
CPU | • Dual Cortex-A72 + quad Cortex-A53 core CPU structure |
• Frequency up to 1.8GHz |
GPU | • Mali-T860MP4 GPU, supports OpenGL ES1.1/2.0/3.0/3.1, OpenVG1.1, OpenCL, DX11 |
• Support AFBC (frame buffer compression) |
NPU | • Support 8bit/16bit operation |
• Support TensorFlow, Caffe model |
RAM | • Dual channel DDR3-1866/DDR3L-1866/LPDDR3-1866/LPDDR4 |
• Support eMMC 5.1, SDIO3.0 |
multimedia | • Support 4K VP9 and 4K 10bits H265/H264 video decoding, up to 60fps |
• 1080P multi-format video decoding (VC-1, MPEG-1/2/4, VP8) |
• 1080P video encoding, support H.264, VP8 format |
• Video post processor: de-interlacing, denoising, edge/detail/color optimization |
Show | • Dual VOP display: resolutions support 4096x2160 and 2560x1600 respectively |
• Support dual-channel MIPI-DSI (4 lines per channel) |
• Display support: eDP 1.3 (4 lines, 10.8Gbps) |
• HDMI 2.0 supports 4K 60Hz display, supports HDCP 1.4/2.2 |
• Support DisplayPort 1.2 (4 lines, up to 4K 60Hz) |
• Support Rec.2020 and Rec.709 color gamut conversion |
interface | • Dual ISP pixel processing capacity up to 13MPix/s, support dual camera data input at the same time |
• Support USB3.0 Type-C interface |
• Suppor PCIe 2.1 (4 full-duplex lanes ) |
• Built-in low-power MCU |
• Support 8-channel digital microphone array input |