# Intelligent toy tracking trajectory design based on mobile cloud terminal deployment and depth-first search algorithm

## TL;DR

This paper introduces a new method for tracking intelligent toys using cloud-based deployment and a depth-first search algorithm to improve tracking accuracy.

## Contribution

A novel toy tracking method combining Transformer-based detection and depth-first search with LSTM for multi-target tracking in mobile cloud environments.

## Key findings

- The proposed detection model achieves an mAP value of 0.858, reaching world-leading performance.
- The tracking method achieves a MOTA value of 0.916, demonstrating excellent multi-target tracking accuracy.
- A lightweight deployment method is proposed for mobile cloud terminals to maintain optimal performance.

## Abstract

The popularization of intelligent toys enriches the lives of the general public. To provide the public with a better toy experience, we propose the intelligent toy tracking method by the mobile cloud terminal deployment and depth-first search algorithm. Firstly, we construct a toy detection model via Transformer, which realizes the positioning of toys in the image through the refined region adaptive boundary representation. Then, using these detected continuous frames, we improve the toy tracking based on a depth-first search. Long-short-term memory (LSTM) constructs the continuous frame tracking structure, and the depth-first search mechanism is embedded to realize the accurate tracking of multiple targets in continuous frames. Finally, to realize the terminal marginalization of the proposed method, this chapter proposes a lightweight model deployment method based on mobile cloud terminals to realize the maintenance of the optimal machine state of intelligent toys. The experiment proves that our proposed target method can reach the world-leading level and obtain the mAP value of 0.858. Our tracking method can also perform excellently with a MOTA value of 0.916.