Detection & Analysis of Shipping Activity using Radar Remote Sensing
- Arpit Shah
- Apr 20, 2020
- 4 min read
Updated: 2 days ago
Satellite Imagery can be utilized in several geospatial workflows. Prior to writing this article, I had already shared one such workflow—Air Pollution Monitoring using Sentinel-5P multispectral satellite data.
In this post, I will cover two cases of Ship Detection using Sentinel-1 SAR satellite data:
in the Gulf of Kutch, to study the change in maritime activity due to India’s nationwide Coronavirus lockdown, and
in the Suez Canal, to observe maritime conditions before, during, and after the stranding of the massive Ever Given container vessel
As always, my aim through this professional blog is to demonstrate—through small, relatable case studies—the scope and benefits of using Location Intelligence to analyse, monitor, and improve operations.
The methodology for performing ship detection using Radar Remote Sensing can be accessed here. A CFAR algorithm was one of the techniques used during the processing workflow. (The same methodology can also be applied to detect icebergs in polar regions.)
SHIP DETECTION IN THE GULF OF KUTCH, INDIA TO STUDY THE IMPACT OF CORONAVIRUS LOCKDOWN ON MARITIME TRADE
After processing two Sentinel-1A Ground Range Detected datasets, the final output is shown below:
As you will infer, a 37% reduction in maritime activity was observed during the nationwide lockdown in 2020 compared to the same period one year earlier.
How accurate is this output?
The imagery was captured by the Sentinel-1A satellite which has a spatial resolution of 5 m × 20 m. The minimum detectable object size was set at 30 metres in length. Reducing this threshold would increase the number of false detections—objects at sea that are not ships may be mistakenly classified as ships.
Object Detection using SAR is based on how microwaves interact with surface features. Sentinel-1 carries an active emitter (C-SAR), meaning the source of illumination is onboard the satellite. Ships reflect a large amount of energy and therefore appear bright in the imagery; surrounding water reflects very little energy and appears dark refer Figure 2.
The accuracy of ship detection depends on several factors: the structure of the object, the type of illumination, the processing methodology, and practical knowledge of the study area.
How to interpret these results?
A reduction in maritime activity was expected during the nationwide lockdown, and a ~37% drop seems plausible. A few points to note:
a) Not all detected objects are commercial cargo or crude-oil vessels (i.e., those indicative of maritime trade). Some may be security vessels, navy vessels, or even pirate boats. Some detections may represent non-vessel objects such as offshore Oil Rig. However, vessels clustered around Mundra Port and Kandla Port—major maritime hubs—are most likely commercial cargo vessels.
b) Because I used a 30-metre object filter, most smaller non-commercial vessels would be omitted. The difference in commercial vessels between the two timelines—148—is therefore meaningful.
c) Not all detected vessels are active. Several ships clustered along the coastline may be docked, abandoned, or undergoing maintenance.
d) This comparison uses only two points in time, roughly one year apart. A multi-temporal analysis would allow for stronger conclusions regarding the lockdown’s impact on maritime activity.
SHIP DETECTION IN THE SUEZ CANAL IN EGYPT TO STUDY THE MARITIME ACTIVITY PRE, DURING & POST THE EVER GIVEN SHIP STRANDING
The grounding of Ever Given—the Taiwanese mega container vessel—at the southern end of the Suez Canal disrupted one of the world’s most crucial maritime routes, which accounts for nearly 12% of global trade. The incident sent economic shockwaves across the globe, including in India, and underscored how deeply interconnected our supply chains are.
Inspired by Google Earth’ Timelapse feature, here is my short timelapse of maritime activity in the Suez Canal over the past month (pre-, during-, and post-stranding), detected using Sentinel-1 SAR Imagery:
Interesting, isn't it?
Satellite imagery, when combined with geospatial tools, is used by security professionals to compare reported vessel positions (reporting is mandatory above a certain ship size) with actual vessels detected via remote sensing. This helps identify and track “dark ships”—vessels that intentionally hide their location because they may be involved in smuggling or other illegal activities.
Similarly, icebergs and oil spills can also be detected using object-detection algorithms applied to radar imagery.
Refer to my complete Remote Sensing work from this link - you will find new and interesting use cases involving object detection, such as this one.
ABOUT US - OPERATIONS MAPPING SOLUTIONS FOR ORGANIZATIONS
Intelloc Mapping Services, Kolkata | Mapmyops.com offers a suite of Mapping and Analytics solutions that seamlessly integrate with Operations Planning, Design, and Audit workflows. Our capabilities include — but are not limited to — Drone Services, Location Analytics & GIS Applications, Satellite Imagery Analytics, Supply Chain Network Design, Subsurface Mapping and Wastewater Treatment. Projects are executed pan-India, delivering actionable insights and operational efficiency across sectors.
My firm's services can be split into two categories - Geographic Mapping and Operations Mapping. Our range of offerings are listed in the infographic below-
A majority of our Mapping for Operations-themed workflows (50+) can be accessed from this website's landing page. We respond well to documented queries/requirements. Demonstrations/PoC can be facilitated, on a paid-basis. Looking forward to being of service.
Regards,
