Deep Learning-based Object Detection using ERDAS IMAGINE can streamline the process of identifying and mapping features such as oil palm growth locations from aerial and satellite imagery. Object detection is the process of recognizing the location of an object or attribute, such as an Oil Palm, or a vehicle, or storage tanks, or solar panels, etc. Basically any type of object which has a reasonably standardized spatial structure in the imagery it occurs in.
|Counting Palm Trees|
Rather than going into a lot of background on the reason for these spatial models please review this short Blog:
...and then the short "how to" video I made:
The general Object Detection workflow is also documented in the Help provided with ERDAS IMAGINE and Spatial Modeler, or that is available online here:
The spatial models provided here will detect and generate bounding boxes of Palm Trees from an image using CNN based Deep Learning. But the basic principles can be applied to any type of object detection. The generation of object detection bounding boxes is performed in a three-step process.
|Collecting training sample footprints|
|Train a Machine Intellect to Detect Palm Trees.gmdx|
|Summary Report sub-model|
|Detect Palm trees from images using DL.gmdx|
Open source data provided in the Download was provided by OpenAerialMap
When unzipped the following directories should be provided from the Download