EcoQuest: put your phone away and let an open model check your discoveries
说明与用途
EcoQuest 让用户在户外行走时仅在发现物体时拍照,开放式 AI 模型验证照片是否符合任务,生成简短的发现记录。
问题
Outdoor apps often force users to stare at screens, reducing real-world engagement.
结果
EcoQuest enables low-attention outdoor exploration by leveraging an open AI model to verify discoveries, producing a simple record without requiring accounts or location tracking.
工作流
- Start expedition – view safety notice and keep phone in pocket
- Pick a mission – receive clear instruction
- Walk and take photo when something matches the mission
- Upload photo – inference service runs SigLIP2 and returns a confidence score
- App marks mission as complete or unverified based on threshold
- View results – short record of discoveries
证据
EcoQuest does the opposite. You pick an expedition, put your phone in your pocket, walk, and take a photo only when you find something. An open-weight AI model checks whether the photo matches the mission, and at the end you get a short record of what you discovered.
The inference service (<code>inference/</code>) Implemented; 27 tests; tested with the real model and with synthetic images
The model is google/siglip2-base-patch16-256, an open-weight vision-language model under Apache-2.0. It runs zero-shot: each mission has a few text prompts…
The thresholds are provisional. They were tuned on 42 Wikimedia Commons photos, not on photos from the park or taken with a phone, so I have not yet measured how the model does on real park photos.
- 记录日期: 2026-10-12T06:41:10.262Z