> For the complete documentation index, see [llms.txt](https://chihinchans-organization.gitbook.io/toronto-unique-moving-ai-initiative/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://chihinchans-organization.gitbook.io/toronto-unique-moving-ai-initiative/toronto-unique-moving-ai-initiative.md). # Toronto Unique Moving AI Initiative ![Labeled image showing a chair and a sofa inside a living room, used for object detection testing in a Toronto Moving and Packing AI system.](/files/EFYfZq5b4VYYYxmDDzwP) Our first version of the [Toronto Unique Moving](https://torontoumoving.com/) app focuses on detecting objects in a room using computer vision technologies. The motive behind this initiative is to quickly identify what needs to be moved, what should be protected, what is bulky, what is heavy, and what items might be expensive. There’s some important differences between different computer vision approaches. The first one, called object detection, can tell what objects are in the frame but don’t really track them as unique items. For example, if a blue chair leaves the camera view at 0:05 and shows up again later at 0:10, the system might think it’s two seperate chairs, which obviously not ideal for our case. The second approach, called multi-object tracking (MOT) with identity preservation—such as using Deep SORT or ByteTrack—can consistently identify the same object, even if it exits and re-enters the frame. This is the model we working with at the moment. Eventually, we’ll need to make our own models to better support the specific needs of our operation. One feature we planning to add is size estimation of objects. Knowing the rough size of a wardrobe, for example, is really helpful for our workflow. Even though it might sound hard to do, it's actually possible to a degree by comparing with common things like a door, which is usually same size, and using that to figure out how big other items are. Ultimately, our goal is to have an AI agent gather moving details from clients. The AI agent will ask users to upload a short video of their room, and from there, we can give them a quote based on what we detect needs to be moved. We are already testing this system and very excited to see how AI can be part of our moving business in a way that’s more smart and useful. If you’d like to learn more about what we’re working on, follow our [blog](https://torontoumoving.com/blog). torontoumoving.com And feel free to bookmark us to stay updated with our latest [Toronto moving news](https://torontoumoving.com). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://chihinchans-organization.gitbook.io/toronto-unique-moving-ai-initiative/toronto-unique-moving-ai-initiative.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.