Seeed Studio introduces ESP32-C3-based Modbus Vision RS485 and SenseCAP A1102 LoRaWAN outdoor Edge AI cameras

Seeed Studio has recently released the Modbus Vision RS485 and SenseCAP A1102 (LoRaWAN) outdoor Edge AI cameras based on ESP32-C3 SoC through the XIAO-ESP32C3 module for WiFi and the Himax WiseEye2 processor for vision AI. Both are IP66-rated AI vision cameras designed for home and industrial applications. The RS485 camera is designed for industrial systems and features a Modbus interface, making it suitable for factory automation and smart buildings. The SenseCAP A1102 uses LoRaWAN for long-range, low-power monitoring in remote locations. Both offer advanced AI for tasks like object detection and facial recognition.

Besides its built-in RS485 interface, the Modbus Vision RS485 also supports LoRaWAN and 4G LTE connectivity via external Data Transfer Units (DTUs). With over 300 pre-trained AI models, the camera can do object detection and classification tasks making it suitable for industrial automation, smart agriculture, environmental monitoring, and other AI-driven applications requiring high performance.

The SenseCAP A1102 connects via LoRaWAN (863-928MHz) and supports a transmission range of up to 10 km. The device also includes a built-in 19Ah non-rechargeable battery for 279 days of operation or can be connected to a DC power supply. Three pre-deployed models for human detection, people counting, and meter reading are loaded on the LoRaWAN camera, so its use cases are different than for the RS485 model.

Modbus RS485 Vision (S-VA-01B) and SenseCAP A1102 specifications:

• Core modules
  • Vision AI Processor – Himax WiseEye2 HX6538
    • MCU Cores
      • Arm Cortex-M55  @ 400 MHz
      • Arm Cortex-M55 @ 150 MHz
    • AI accelerator – Arm Ethos-U55 microNPU @ 400 MHz
    • Memory – Up to 2432KB SRAM
    • Storage – 64KB boot ROM
  • WiFi module  – XIAO ESP32C3
    • SoC – ESP32-C3 single-core RISC-V microcontroller @ 160 MHz with 400KB SRAM, 384KB ROM, Wi-Fi 4 & Bluetooth LE 5.0 connectivity
    • Storage – 4MB flash
  • LoRaWAN Module (SenseCAP A1102 only) – Seeed Studio Wio-E5 Module based on STMicro STM32WLE5JC
• Storage – 8GB MicroSD card (Class 10)
• Camera
  • Sensor: OV5647
  • Lens size: 1/4″ sensor
  • 2592 x 1944 resolution
  • 3.4mm focal length (adjustable)
  • 1080p@30fps, 720p@60fps video recording
  • 62° FOV
• Connectivity
  • Modbus RS485 Vision
    • Modbus RS485 via TP8485E supports a half-duplex transceiver and Modbus-RTU protocol (Transmission range 1200 meters speed 250k bps max)
    • Wi-Fi for transmitting keyframes
    • SenseCAP Sensor Hub 4G DTU, SenseCAP S2100 LoRaWAN DTU (for remote transmission)
  • SenseCAP A1102
    • LoRaWAN
      • Protocol – LoRaWAN v1.0.3 Class A
      • Frequency Bands –  IN865/EU868/US915/AU915/AS923
      • Max Transmission Distance – 2–10 km (depending on environment)
      • Max Transmit Power – 19dBm
    • Wi-Fi for sending keyframes
• Power
  • Modbus RS485 Vision – 5V/12V input with 1A max current
  • SenseCAP A1102
    • Built-in 19Ah Non-rechargeable D-size Li-SOCl2 battery (279 days of operation at 5-minute intervals)
    • Optional DC 12V/1A power supply (requires junction box)
• Dimensions – 180 × 75 × 70mm
• Weight
  • Modbus RS485 Vision – 439 grams
  • SenseCAP A1102 – 719 grams
• Environmental
  • IP66-rated (dustproof, water-resistant)
  • Operating Temperature – 0 – 70°C
  • Operating Humidity – 0 – 100 %RH (non-condensing)
• Cable Length – 2 meters

More information about the Modbus RS485 outdoor Edge AI camera can be found on the wiki which includes a features overview, specifications, and instructions explaining how to deploy both factory-installed and custom AI models, how to read data from the camera using XIAO, and how to transmit data via RS485. The SenseCAP A1102 outdoor Edge AI camera has its own wiki entry with similar instructions, but additional information about power usage and LoRaWAN connectivity.

The SenseCraft App makes configuration easy, including adjusting model confidence thresholds, switching between pre-installed models, and binding the camera to a data logger. For custom AI models, both cameras work with the SenseCraft AI platform, which provides access to over 300 pre-trained models and supports TensorFlow and PyTorch frameworks (TensorFlow Lite for the SenseCAP A1102). This platform also enables users to deploy custom models without any coding expertise.

The Seeed Studio Modbus RS485 vision AI camera is priced at $39.00 and the SenseCAP A1102 outdoor Edge AI camera goes for $75.00.

Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress