xby-pedestrian
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-pedestrian
Paste the following prompt into your AI chat to install this plugin:
Run the install command in the DeepSeek Harness terminal to add the plugin; the source code is available at https://github.com/xby-skill/xby-pedestrian .
About this plugin
Pedestrian detection is one of the most frequently needed tasks in any computer vision pipeline. The xby-pedestrian plugin wraps this inference capability into a conversational tool inside DeepSeek Harness, so developers can call the model and retrieve results directly from chat without spinning up a GPU box or managing a separate inference service.
Under the hood, the plugin accepts images through three channels: a public URL, a Base64-encoded string, or a local file path, making it easy to work with both online assets and offline datasets. Every call returns bounding-box coordinates, confidence scores, and class labels for each detected pedestrian, structured for immediate use in visualization, tabulation, or annotation validation. The API key is set with a single in-chat command and persists across sessions, removing repetitive configuration overhead.
It is well suited for developers building intelligent surveillance, smart-transportation, or human-machine-interaction systems, as well as researchers who need quick, reproducible pedestrian-detection results for data annotation checks or quantitative analysis.
Use Cases
- Pedestrian identification and counting in smart surveillance
- Pedestrian state analysis in smart transportation
- Annotation validation and data verification for detection results
Best For
- Developers building intelligent surveillance systems
- Researchers needing quick pedestrian detection calls
- Computer vision engineers performing annotation validation
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.