Artificial Intelligence 8 min read

Award-Winning AIoT Projects from the 2021 TencentOS Tiny AIoT Innovation Competition

The 2021 TencentOS Tiny AIoT Innovation Competition showcased over 50 original projects, including award‑winning multi‑functional pedestrian detection devices, AI‑enhanced smart wheelchairs, and endangered‑animal recognition systems, each demonstrating low‑power embedded AI, edge computing, and cloud integration for diverse real‑world applications.

Tencent Architect
Tencent Architect
Tencent Architect
Award-Winning AIoT Projects from the 2021 TencentOS Tiny AIoT Innovation Competition

The 2021 TencentOS Tiny AIoT Innovation Competition attracted more than 50 original submissions from developers and IoT enthusiasts across China, covering smart home, animal protection, education, transportation, agriculture and other fields.

Among the winners, the first‑place “Multi‑functional Pedestrian Detection Instrument” uses an embedded AI model accelerated by CMSIS‑NN on boards such as NXP RT1062, STM32H750 and low‑power STM32L496, providing pedestrian recognition, counting and abnormal‑stay detection for traffic monitoring, epidemic control and security.

Key highlights include a compact deep‑learning model, minimal memory footprint, and integration with Tencent Lianlian mini‑program for real‑time cloud reporting.

The second‑place “TencentOS Tiny AIoT Development Board in Smart Wheelchair” adds remote control, multi‑modal perception (posture, speed, temperature, humidity, light) and cloud connectivity, enabling wheelchair elevation, lighting and status monitoring via a WeChat/APP mini‑program.

Its architecture consists of a remote layer (mini‑program), a main‑control layer with AIoT board and Wi‑Fi, a communication layer, a perception layer for sensor data, and a driver layer for motor and LED control.

The third‑place “Endangered‑Animal Outdoor Target Recognition and Tracking System” adapts YOLO‑v3 for MCU deployment using TensorFlow Lite Micro, reducing model size and parameters to run on a single‑chip, and uploads detection results to Tencent Cloud, greatly improving storage efficiency and reducing manual screening.

Experts praised the projects for demonstrating complete AIoT system construction—from model training and testing to deployment and application development—showing high portability, low cost, low power consumption and broad application potential.

TencentOS Tiny, a lightweight, modular, secure IoT operating system, provides the foundation for these AIoT solutions and the competition aims to foster further technical exchange and innovation in the “万物智联” era.

computer visionEdge ComputingAIoTTencentOS TinyEmbedded AISmart Devices
Tencent Architect
Written by

Tencent Architect

We share insights on storage, computing, networking and explore leading industry technologies together.

0 followers
Reader feedback

How this landed with the community

login Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.