[ad_1]
It’s always fun to look at aerial and satellite maps of places we know, seeing a different perspective than our usual ground level view. We lose that context when it’s a place we don’t know by heart. Like, say, Mars. So [Matthew Earl] sought to give context to the Perseverance rover landing video by projecting onto orbital images of ESA’s Mars Express. The resulting video (embedded below the break) is a fun watch alongside the tech writing Reprojection of Perseverance landing images onto satellite images.
Some telemetry data of the rover’s position and bearing was transmitted live during the landing process, with the rest being recorded and uploaded later. Surprisingly, none of this information was used for this project, which was based entirely on video pixels. This makes the results even more impressive and the techniques more widely applicable to other projects. The fundamental part is SIFT (Scale Invariant Feature Transform), which is one of the many tools in the OpenCV toolkit. SIFT found correlations between the video frames from Perseverance and the orbital image from Mars Express, fueling a processing pipeline written in Python for the results rendered in Blender.
While many elements of this project seem appealing to robotic vision applications, there are a few challenges addressed in the “Final touches” section of the editorial. The fall of the heat shield interfered with automated tracking, implying that this process will need help to fully understand the dynamically changing environments. Also, it doesn’t seem to run fast enough for a robot’s real-time needs. But at first glance, these problems are not fundamental. They are just waiting for motivated people to tackle the future.
This process has some superficial similarities to projection mapping, which is a category of projects that we have featured on these pages. Except that everything is reversed (camera instead of video projector, etc.) making the calculation a completely different box of worms. But if you’re more interested in projection mapping, here’s a place to start.
[via Dr. Tanya Harrison @TanyaOfMars]
[ad_2]
Source link