Understanding Sensor Fusion and Tracking, Part 5
The fifth installment of this Matlab video series discusses the challenges of fusing data from multiple objects.
The importance of sensor fusion is growing as more applications require the combination of data from different sensor inputs. Self-driving cars, radar tracking systems, and the IoT are some key applications.
In the fifth installment of this video series, Matlab looks at multiple object tracking. Unlike tracking a single object, multiple objects present greater challenges lie in know which object the observed data is originating from. This may not be an issue when objects are spaced apart, but an issue when objects are close together. The video also notes that object data may need to be added or deleted to minimize the likelihood of false detection.
According to the video, users need to carefully match observation to a tracked object. Creating the correct algorithm to accurately track objects goes a long way. Once the user sets up tracking algorithms, he/she can then run estimation filters for each of the tracked objects. A gating method can be used to speed assignments and weed out undesired data.
You can view the video here.
About the Author
You May Also Like