Replace Ultrasonic Bin Sensors with On-Device Vision AI

The Integration Problem You’re Actually Solving

Most waste bin monitoring projects land with a line item already filled in: ultrasonic fill sensors. They’re cheap, well-understood, and have a long track record in smart city deployments. But there’s a gap between what the spec sheet says and what the sensor delivers when you’re trying to push reliable data into a routing or alerting system at scale.

The problem isn’t that ultrasonic sensors are bad technology. The problem is that they produce a single scalar value — distance in centimetres — and expect your downstream system to make complex operational decisions from it. When your client asks “why did the truck go to an empty bin?” or “why did this bin overflow if the sensor said 60%?”, the answer is almost always in the gap between what the sensor measured and what was actually in the bin.

Why Ultrasonic Sensors Fail in Waste Bin Monitoring

Ultrasonic sensors work by emitting a sound pulse and measuring the time to bounce back from the nearest surface. In a clean cylindrical tank, that’s reliable. In a waste bin, you’re dealing with irregular materials, varied surface textures, and unpredictable geometry — and the physics of acoustic reflection don’t handle that consistently.

How On-Device Vision AI Works Differently

The NeoEyes NE301 uses an STM32N6 processor with a NPU (Neural Processing Unit — a chip module purpose-built to accelerate AI inference). The camera captures a frame of the bin’s current state, runs a trained classification model directly on the NPU, and produces a fill-level result in under 50ms — entirely on-device, with no cloud dependency. The result is published via MQTT or HTTP to your backend.

At 0.6 TOPS (tera operations per second), the NPU is sufficient for running quantised YOLOv8 classification models native to the NE301’s firmware. This is the architectural fact that separates it from cameras using general-purpose MCUs: the dedicated NPU handles the inference workload without competing with network I/O or sensor management tasks.

Multi-Class Output — Not a Distance or a Boolean

A vision model returns whatever classes you train it on. A typical waste bin monitoring model uses 6 classes, each mapping to a different action in your alerting logic:

The two classes at the bottom — overflow (waste piled outside the bin) and contaminated (hazardous or mixed-stream waste) — are invisible to any sensor measuring internal fill depth. These are the conditions that generate the most expensive operational responses, and they are the ones a sensor-based deployment systematically misses.

The MQTT Payload Your Backend Receives

When the NE301 publishes inference results, each MQTT message includes the classification label, confidence score, estimated fill percentage, and a reference to the captured image stored on-device. Here is the payload structure:

{
    "device_id":     "ne301-bin-042",
    "timestamp":     "2026-03-24T08:14:22Z",
    "location":      "zone-B / stand-12",
  
    // Inference result from Neural-ART NPU
    "fill_class":    "near_full",      // empty | partial | near_full | full | overflow | contaminated
    "confidence":    0.91,              // recommended dispatch threshold: ≥ 0.80 for overflow / contaminated
    "fill_pct_est":  72,               // estimated fill % from model (informational)
  
    // Image reference (stored on-device, fetched via HTTP)
    "image_url":     "http://192.168.1.42/snap/20260324_081422.jpg",
    "image_size_kb": 91,
  
    // Device health
    "battery_pct":   84,               // NE301 supports PoE, USB, or battery
    "signal_rssi":   -61,
    "fw_version":    "1.4.2"
  }

Hardware Selection for Bin Monitoring Deployments

The right hardware depends on power availability, inference requirements, and scale. For waste bin monitoring specifically, there are two distinct deployment architectures:

NeoEyes NE301

Primary · On-Device AI Camera

Inference on-device — no server needed per bin

• STM32N6 + NPU · 0.6 TOPS
• YOLOv8 · <50ms inference latency
• 4MP MIPI CSI · 51°/88°/137° FOV options
• Deep sleep 7–8 µA · PoE, USB, or battery
• IP67 weatherproof · 77×77×48 mm
• WiFi 6 · BT 5.4 · optional LTE Cat.1 or PoE

$199.90–$258.00 Buy NE301

NeoEdge NG4500

Edge Server · Multi-Camera Hub

Centralised inference for large-scale networks

• NVIDIA Jetson Orin NX/Nano · up to 157 TOPS
• Aggregates feeds from multiple cameras
• Supports VLM / LLM edge inference
• JetPack 6.0+ · mainstream DL frameworks
• Fanless chassis · 12–36V DC
• CAN · RS232 · RS485 · multi I/O

From $899.00 Shop Now

Full Comparison Across Deployment Dimensions

Accuracy at Scale: What the Numbers Mean at 100 Bins

NE301 accuracy: CamThink field validation with custom YOLOv8 model. Sensor figures: field-reported averages, IoT Analytics 2023.

At 100 bins monitored 4× per day, a 68% accurate ultrasonic sensor generates approximately 128 incorrect readings every 24 hours. Each false “full” reading risks an unnecessary truck dispatch. Each false “not-full” reading risks a missed pickup and visible overflow. At that noise level, dynamic routing stops working — operators revert to fixed schedules because they can’t trust the data, which defeats the purpose of the monitoring system.

At 94% accuracy, 100 bins × 4 readings produces roughly 24 incorrect readings per day — and each one comes with a timestamped image that lets your system, or a human reviewer, immediately determine whether the error is a model issue, an unusual waste type, or an occlusion. Those images become your retraining dataset.

Training a Waste Bin Detection Model for NE301

The NE301 runs quantised YOLOv8 models natively via its NPU. The model pipeline is open: you train on your own dataset, export to INT8 quantised format, and deploy via the NE301 Web UI or OTA update — no proprietary toolchain required.

Dataset Collection

You need representative images for each fill class from the actual bin types in your deployment. A minimum viable 6-class waste model requires approximately 200–400 images per class captured under realistic conditions — including varying lighting, weather, and waste types. The critical classes to deliberately over-represent during collection are overflow and contaminated: these are rare in real operation, so you need to stage them. A model trained on an imbalanced dataset will systematically under-detect exactly the conditions that matter most.

from ultralytics import YOLO
  
  # YOLOv8n-cls — nano classification variant, suitable for NE301 NPU
  model = YOLO('yolov8n-cls.pt')
  
  results = model.train(
      data='waste_bin_dataset/',   # directory: train/ val/ per-class folders
      epochs=80,
      imgsz=320,               # NE301 optimal input resolution
      batch=32,
      patience=15,
      project='bin_monitor',
      name='ne301_waste_v1'
  )
  
  # INT8 quantisation: compresses weights from 32-bit float to 8-bit integer
  # Result: ~4× smaller model, ~2–3× faster inference on NPU, <2% accuracy loss
  model.export(
      format='tflite',
      int8=True,
      data='waste_bin_dataset/data.yaml'
  )
  # Output: best_int8.tflite — flash to NE301 via Web UI or OTA

Deployment Phases: From PoC to Production Network

FAQ