xby-detect-vehicle
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-detect-vehicle
Paste the following prompt into your AI chat to install this plugin:
Clone the plugin source from https://github.com/xby-skill/xby-detect-vehicle and run dsh plugin install xby-skill/xby-detect-vehicle in DeepSeek Harness to complete installation.
About this plugin
In smart traffic, parking lot management, and incident forensics, quickly identifying vehicle types in images is a core need. xby-detect-vehicle was built for exactly that: feed in an image and it will detect vehicles (car, truck, bus, motorbike, tricycle, carplate), returning bounding boxes, confidence scores, and class labels for every target without requiring you to spin up your own inference stack.
The plugin supports three input modes: image URL, Base64-encoded data, and local file path, covering web front-end, back-end service, and local debugging scenarios. The API key is set once via a chat command and persists automatically across restarts, eliminating repetitive configuration.
It is ideal for developers who need vehicle detection directly inside a conversation: automating traffic data labeling, building smart parking systems, or adding a visual perception node to an Agent workflow. Install and go, focusing on business logic rather than model deployment details.
Use Cases
- Classify vehicle types and positions in traffic surveillance images
- Detect vehicles and capture plates in parking entry/exit images
- Add a visual perception node to an Agent workflow
- Batch-process surveillance images and export structured detection results
Best For
- Traffic-domain developers who need quick vehicle detection calls
- Engineers building smart parking or incident forensics systems
- Developers adding visual perception to Agent workflows
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.