The sensor optimization deployment is a multi-objective optimization problem involving sensor coverage effectiveness, frequency conflict probability, and resource utilization. The existing sensor optimization deployment methods mostly adopt weighted approaches to transform multiple optimization objectives into a single objective problem for resolution, which not only relies on prior knowledge but also leads to the loss of diversity in optimal solutions. To address these issues, a Collaborative evolution Multi-Objective Particle Swarm Optimization (CoMOPSO) algorithm is proposed. It designs a collaborative evolution framework that guarantees the convergence of high-dimensional problems through the convergence of the population, and rapidly approaches the Pareto optimal frontier. The diverse population uses the ∈-dominance method to ensure the integrity and diversity of the global and local optimal solution sets. A fast non-dominated sorting and elite individual preservation strategy is employed to enhance the quality of solutions. Experimental results demonstrate that, for the sensor optimization deployment problem, the proposed method outperforms traditional optimization algorithms in terms of Inverted Generational Distance (IGD) and indicators, exhibiting better convergence and diversity and effectively improving the performance of sensor networks.