This work proposes an embedded system that opportunistically detects free on-street parking by using surveillance cameras. Intelligent boards are embedded in the cameras allowing a distributed processing and communication. The task of looking for free parking spaces demands a significant amount of drivers' time. This problem generally takes place in urban areas where there is a large number of vehicles and few available parking spaces (on-street or off-street). Decreasing the time spent in this task could reduce the traffic jam or, in an extreme perspective, alleviate the toxic gases emission or the fossil combustible consumption. Initially, it was evaluated three classical techniques for image processing applied to detect free on-street parking. The best one presents a success detection rate close to 100%. After that, it was evaluated the performance of the embedded system by using only the best image processing technique. This performance evaluation considers three different scenarios: centralized, hybrid, and embedded. The last one is the main proposal and contribution. The results reveal that embedded proposal had an average requisition time of 2.10 s vs. 0.38 s of centralized one. The hybrid one presents the worst results.