top of page

Detection & Analysis of Shipping Activity using Radar Remote Sensing

Writer: Arpit ShahArpit Shah

Updated: Feb 22

Satellite Imagery can be utilized in several geospatial workflows - prior to writing this article, I had already posted about one such workflow - that of Air Pollution Monitoring using Sentinel 5-B multispectral satellite data.


In this post, I will cover two cases of Ship Detection using Sentinel-1 SAR satellite data -

  1. in the Gulf of Kutch in order to see the extent of change in maritime activity due to the prevalent Coronavirus lockdown conditions, and

  2. in the Suez Canal in order to see the extent of change in maritime activity due to the stranding of the massive Ever Given container cargo vessel.


As alway, my aim through this professional blog is to demonstrate, using small and relatable case studies, the scope and benefits of deploying Location Intelligence with the objective to analyze, monitor and improve Operations.


The method of performing ship detection through Radar Remote Sensing can be accessed here - CFAR algorithm was one of the techniques used during the Processing workflow - the same methodology can be used to detect Icebergs in Polar regions.

 

SHIP DETECTION IN THE GULF OF KUTCH, INDIA TO STUDY THE IMPACT OF CORONAVIRUS LOCKDOWN ON MARITIME TRADE


Upon processing two Sentinel-1A Ground Range Detected datasets, the final output is depicted in the map below-

I have used data for this study.

Object (Ship Detection) in Gulf of Kutch - 2019 vs 2020 - extracted using SAR (Sentinel-1) Imagery
Figure 1: Ship Detection in Gulf of Kutch - 2019 vs 2020 - extracted using SAR (Sentinel-1) Imagery

As you will infer, a 37% reduction in maritime activity has been observed during the nation-wide coronavirus lockdown in 2020 compared to normal conditions one year prior.  

How accurate is this output?


The Imagery has been captured by Sentinel-1A satellite which has a spatial resolution of 5 m by 20 m. The parameter for objects to be detected was kept at a minimum of 30 meters in length. Reducing it further would increase the number of False Detections i.e. some at-sea objects would be wrongly classified as ships.


Object Detection is possible based on the principle of how microwaves interact with surface features (Note: Sentinel-1 has an active emitter i.e. the source of illumination is onboard the satellite itself - the C-SAR instrument). A Ship's backscatter is bright i.e. the reflected energy is large. In comparison, the backscatter from surrounding Water is dark as the reflected energy is negligible - refer Figure 2.


The extent of accuracy of Ship Detection depends on aspects such as structural properties of the object, type of illumination, methodology of processing the imagery dataset, and having practical knowledge about the study area.

Ships appear brighter in SAR Imagery as compared to the dark water in background. This contrast facilitates ship detection using radar (SAR) satellite imagery.
Figure 2: Ships appear brighter in a SAR Imagery product as compared to the dark water in background. This contrast facilitates ship detection using radar (SAR) satellite imagery.

























How to interpret these results?


A reduction in maritime activity was expected given the nation-wide coronavirus lockdown and ~37% seems plausible to me. Certain aspects to note, however, are-


a) Not all Shipping objects are Commercial Cargo vessels or Crude Vessels - indicative of Maritime Trade. Some of the detected objects can be Security Vessels, Navy Vessels or even Pirate vessels. Besides, some detections may not be vessels at all but other objects at sea - for example, an offshore Oil Rig. However, one can safely assume that the vessels clustered around Mundra Port and Kandla Port - major maritime centers in this region - would likely be Commercial Cargo vessels.


b) Also, given that I've used an Object Size of 30 m as a filter, Ships of the non-Commercial variety would typically be omitted from the detection. As a result, the difference in Commercial vessels between the two Imagery timelines - 148 - is significant.


b) That being said, not all Shipping Objects detected are Active i.e. are operational vessels - as you will observe, a sizeable number of Ships are clustered around the coastline. Many of these could be docked vessels or abandoned vessels or vessels that are undergoing maintenance.


c) The comparison has been made using two points in time, roughly one year apart. Adding more observations i.e. performing a multi-temporal analysis would help in drawing a better conclusion about the impact on maritime activity due to the lockdown.

 

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 in Egypt and the resulting blockage in maritime activity in this narrow albeit crucial Shipping route which accounts for 12% of the world's trade has sent economic shockwaves across the world, including in India. This unfortunate incident is an acute reminder of the interdependency in global and how a disruption at a particular node can trigger chaos across the Supply Chain.


Drawing inspiration from a wonderful tool in Google Earth - the Timelapse, here is my short Timelapse version of maritime activity in the Suez Canal over the last month (pre, during, and post the vessel stranding), as detected using Sentinel-1 SAR Imagery again-

Video 1: Timelapse of Ship Detection in the Suez Canal - Pre, During & Post the Ever Given Cargo Vessel stranding on 23rd March 2021 to study the impact on Maritime Trade

Interesting, isn't it?

 

Satellite Imagery, in combination with geospatial tools, are used by Security professionals to compare the reported records of vessel whereabouts (reporting is mandatory for ships above a certain size) with the number of actual vessels detected at sea derived from Remote Sensing as demonstrated here. This is done to spot the presence of and track Dark Ships - those vessels that do not report their whereabouts as they may be participating in Smuggling and other illegal / anti-national activities. Icebergs and Oil Spills can also be detected using Object Detection algorithms.


Refer my complete Remote Sensing work from this link - you'll be sure to find new use cases involving Object Detection every now and then, such as this.

 

ABOUT US


Intelloc Mapping Services, Kolkata | Mapmyops.com offers Mapping services that can be integrated with Operations Planning, Design and Audit workflows. These include but are not limited to Drone Services, Subsurface Mapping Services, Location Analytics & App Development, Supply Chain Services, Remote Sensing Services and Wastewater Treatment. The services can be rendered pan-India and will aid your organization to meet its stated objectives pertaining to Operational Excellence, Sustainability and Growth.


Broadly, the firm's area of expertise can be split into two categories - Geographic Mapping and Operations Mapping. The Infographic below highlights our capabilities-

Mapmyops (Intelloc Mapping Services) - Range of Capabilities and Problem Statements that we can help address
Mapmyops (Intelloc Mapping Services) - Range of Capabilities and Problem Statements that we can help address

Our Mapping for Operations-themed workflow demonstrations can be accessed from the firm's Website / YouTube Channel and an overview can be obtained from this brochure. Happy to address queries and respond to documented requirements. Custom Demonstration, Training & Trials are facilitated only on a paid-basis. Looking forward to being of service.


Regards,

Mapmyops I Intelloc Mapping Services

Mapmyops
  • LinkedIn Social Icon
  • Facebook
  • Twitter
  • YouTube
Intelloc Mapping Services - Mapmyops.com
bottom of page