Co-registration vs georeferencing, and orthorectification Georeferencing is the process of establishing a spatial relationship between an image pixel and its corresponding position within a geographic coordinate system. This procedure enables precise locations of objects within the captured scene. Ortho-rectification eliminates parallax effects, addressing not only those associated with ground-level relief but also those related to…

As we’ve already seen in this post, in general the computer vision field has an “object” type approach, while other approaches in the remote sensing field work very much with “pixel” type algorithms. This sometimes leads to far-fetched discussions about “which performance curves should I calculate”, are they comparable? Here…

Part 2 —Detection — In this second part, we focus on the advancements of deep learning in the field of object detection in Synthetic Aperture Radar (SAR) images. This topic is not new. Deep learning is gradually making its way into object detection in radar images, but still in a somewhat nascent stage. Some vocabulary To…

Part 1 — Segmentation — The current efforts in AI make it extremely challenging to maintain competitiveness in the quest for superior algorithm performance, which often requires huge datasets and significant computing power. In this context, SAR images remain a relatively unexplored area. Instead of starting from scratch in this remote sensing field, it is…

Sentinel-1 time series are becoming more and more accessible. You may wonder what to do with the polarimetric information in the (VV,VH) or (HH,HV) stripmap modes. The good news is that even if you don’t have all the information in the Sinclair matrix, you can still do quite a bit…

One of the first scattering mechanism studied in polarimetry is the “double bounce”. It is everywhere, as soon as the ground is horizontal, and an object has a vertical axis. One of the first canonical targets studied in polarimetry that implies “double-bounce” is the dihedral, such as that formed by…

Or how to represent a complex interferometric coherence in colors? — Radar interferometry assumes that we have a pair of complex input images, Z1 and Z2, that have been previously co-registered to each other. (In the following, we consider images that we have already registered to each other) We then calculate the interferometric coherence parameter, using convolutions, as previously explained here:

By verifying that the center of the spectrum is at the extremities — An SLC image does not have classical statistics, as we saw here. To oversample it as cleanly as possible, it is a matter of operating on the complex spectrum, adding zeros around it, and then doing the reverse ifft. …

And what are its statistical properties? — At the origin of speckle: “Random Phasor Sums” Speckle is inherent in the formation of the radar image. Joseph Goodman models the signal in the resolution cell as the sum of the independent contributions of the scatterers, i.e., complex, independent, identically distributed response elements whose real and imaginary parts are independent [Goodman, 1976].