Détection acoustique, classification, localisation et pistage (DCLP) dans un environnement portuaire

*AMENDMENT 002 IS RAISED TO ANSWER QUESTION FROM THE INDUSTRY.

______________
*AMENDMENT 001 IS RAISED TO ANSWER QUESTION FROM THE INDUSTRY AND TO EXTEND DE SOLICITATION CLOSING DATE.

______________

The ISC Website challenge notification update will be available on 2025-06-26 by end of day.

This Challenge Notice is issued under the Innovative Solutions Canada Program (ISC) Call for Proposals 004 (EN578-24ISC4).
Solicitation Documents reference: https://canadabuys.canada.ca/en/tender-opportunities/…
*For additional general information on the ISC Program, visit: https://ised-isde.canada.ca/site/innovative-solutions…).
_____________

This challenge is only open to receive proposals for Phase 1 (Proof of Feasibility) of our Challenge Stream. Proposed solutions that fall within technology readiness levels (TRL) 1-4 can be submitted to this challenge.

Steps to apply:
Step 1: read this challenge
Step 2: read the Call for Proposals : https://canadabuys.canada.ca/en/tender-opportunities/…
Step 3: propose your solution here : https://ised-isde.canada.ca/site/innovative-solutions…
_____________

Challenge sponsor: Department of National Defense (DND)

Funding mechanism: Contract

Multiple contracts could result from this Challenge:

Phase 1
The maximum funding available for any Phase 1 contract resulting from this Challenge is : $250,000.00 CAD excluding applicable taxes, shipping, travel and living expenses, as required.
The maximum duration for any Phase 1 contract resulting from this Challenge is up to 6 months (excluding submission of the final report).
Estimated number of Phase 1 contracts: 2

Phase 2
Only eligible businesses that have successfully completed Phase 1 will be invited to submit a proposal for Phase 2.
The maximum funding available for any Phase 2 contract resulting from this Challenge is : $1,000,000.00 CAD excluding applicable taxes, shipping, travel and living expenses, as required.
The maximum duration for any Phase 2 contract resulting from this Challenge is up to 12 months (excluding submission of the final report).
Estimated number of Phase 2 contracts: 1
This disclosure is made in good faith and does not commit Canada to award any contract for the total approximate funding. Final decisions on the number of Phase 1 and Phase 2 awards will be made by Canada on the basis of factors such as evaluation results, departmental priorities and availability of funds. Canada reserves the right to make partial awards and to negotiate project scope changes.

Note: Selected companies are eligible to receive one contract per phase per challenge.

Travel: No travel anticipated for Phase 1.
_____________

Problem statement:

Traditional sonar technology relies on complex and power/memory-intensive processing schemes. Some future sonar systems will be transitioning to underwater, autonomous, battery-powered, and standalone (without cables) systems that will be less capable in terms of power, processing, and storage. Those future systems will be equipped with an array of sensors (multiple sensors of the same type), deployed in a wide range of locations, and used for long-term missions thus being subject to the seasonal variabilities and environmental conditions. An example of such systems can be found in Figure 1 of referenceFootnote1 listed below. Those autonomous systems can be deployed as a singleton or as a group, with the latter configuration typically involving a limited amount of data transfer at a low data rate.

This software challenge is meant to explore new approaches that could help develop efficient detection, classification, localization, tracking (DCLT) acoustic data processing solutions that are appropriate for those future autonomous systems.

Applicants (Offerors) qualifying for Phase 1 will receive representative multi-channel acoustic data and non-acoustic data to help develop their proposal. The data will be collected from a busy harbour environment and municipal transit ferries will represent the contacts of interest for the development of DCLT solutions. Candidates qualifying for Phase 2 will receive a larger sample of those datasets. Dataset selection may represent various environmental conditions inclusive of severe weather (heavy rainfalls, strong winds, etc.) and seasonal variations (distinct sound speed profiles). Phase 2 final demonstration will use a new dataset with unusual ferry routes. Successful applicants to Phase 1 of the Challenge will undertake development of a detailed solution concept as a proposal for consideration to progress to Phase 2. Candidates selected to continue to Phase 2 will develop functional solutions for demonstration. Phase 2 will concentrate on solutions that are viable for battery-powered systems with limited computing and communication capabilities.

Acoustic data will originate from two underwater hydrophone (underwater microphone) arrays in a shallow water environment. Non-acoustic data will include sound speed profiles, weather data, orientation data, underwater current data, ferry Global Positioning System (GPS) data, and Automatic Identification System (AIS) data of nearby maritime traffic. All ferries will be equipped with GPS thus providing ground-truth. ReferenceFootnote2 below provides the various features of the data being provided. A definition for false alarm rate calculations for a multi-static scenario can be found in ReferenceFootnote3, Section 3.1. A "false alarm" occurs when a ferry-detection is reported while no ferry is present. The false-alarm rate (FAR) found inFootnote3 is provided as guidance but in general an FAR is computed by reporting the number of false alarms over an observation period (i.e., time). Technical details of the systems collecting data can be found inFootnote4.

Footnote 1
C. Lucas, G. Heard, N. Pelevas, "DRDC Starfish Acoustic Sentinel and Phase Gradient Histogram Tracking", UACE2015 – 3rd Underwater Acoustics Conference and Exhibition, DRDC-RDDC-2015-N035p803408_A1b.pdf(drdc-rddc.gc.ca)

Return to footnote1referrer
Footnote 2
SVT Challenge – Data Format Summary.

Return to footnote1referrer
Footnote 3
Benchmark Evaluation of Multistatic Trackers,https://apps.dtic.mil/sti/tr/pdf/ADA454744.pdf

Return to footnote3referrer
Footnote 4
S.Blouin, M.Morgan, "Semi-Permanent Real-Time Oceanic Sensing Platform for Innovation Challenges", accepted for publication in proceedings if the 19th Annual IEEE International Systems Conference (SYSCON25), April 2025.

Return to footnote4referrer
Desired outcomes and considerations
Essential (mandatory) outcomes
The proposed solution must:

Rely on acoustic data as the basis of the solution during demonstration(s) and potential implementation. identification system (AIS) data, GPS data or the internet are not to be used.
Acoustically detect when ferry traffic is present while recording detection false alarms.
Acoustically localize ferries that are moving and derive a localization-accuracy metric over their terminal-to-terminal routes.
Have a built-in adaptive/robustness scheme mechanism to accommodate for varying environmental conditions, inclusive of higher ambient noise due to shipping traffic or weather.
Have built-in schemes mechanisms to reduce report its requirements in terms of storage, power, and algorithm training (if the latter is required).
Additional outcomes
The proposed solution should:

Provide increased performance in the detection of ferry traffic to the following progressive specifications:
Determine when ferry traffic is present with a 75%, or higher, success rate and 15%, or lower, false-alarm rate; or
Determine when ferry traffic is present, with a 85%, or higher, success rate and 10%, or lower, false-alarm rate; or
Determine when ferry traffic is present with a 95%, or higher, success rate and a 5%, or lower, false-alarm rate.
Note that more difficult specifications are better aligned with the intended goal.

Provide increased performance in the localization of ferry traffic to the following progressive specifications:
localize at least 2-out-of-4 ferries within an accuracy of 400 metres for 25% or more of their overall terminal-to-terminal routes; or
localize at least 3-out-of-4 ferries within an accuracy of 200 metres for 50% or more of their overall terminal-to-terminal routes; or
localize all ferries within an accuracy of 100 metres for 75% or more of their overall terminal-to-terminal routes
Distinguish ferries from one another.
Detect changes in each ferries' acoustic signatures (transient or steady features) over time.
Discern between ferries and ships aligned along similar bearings (separated by less than 10 degrees).
Provide documented design considerations about how to perform DCLT tasks in a distributed manner, which means that only a limited amount of data can be shared between the acoustic systems in a deployed environment.
Provide additional information on addressing:
algorithm computation-and-energy efficiency given the possibility of eventual deployment to a low size, weight, and power (SWAP) device;
how much data is required for algorithm training (if any); and
what changes would be required to classify and localize another type of vessel based on acoustic signature.
Background and context
Canada's recent Defence policy update "Our North, Strong, and Free" clearly stipulates the importance and urgency of monitoring Canadian Arctic waterways that are becoming increasingly accessible due to climate change. The vast expanse of Canada's North, harsh environmental conditions, and lack of infrastructure all create a significant challenge for subsea surveillance and monitoring on a wide scale. The need for long-term deployment of surveillance solutions in remote regions in this challenging operational context could be partially addressed through the use of autonomous acoustic solutions, both fixed-location and mobile. Any solution operating in Canada's expansive and remote geography would need to carry their own power reserves that must be used judiciously.

Development of innovative capabilities to address the challenging and extremely remote operational environment of the North not only supports Canadian national security priorities but also Canadian obligations as part of NORAD and NATO.

Canada has a strong depth of experience related to the gathering, processing, and analysis of acoustic information and has growing capability regarding autonomous solutions and artificial intelligence. These strengths enable the potential to create solutions to address the significant challenge of monitoring the waterways of the arctic for the national security of Canada and our allies. In addition, development of sovereign capability for these national security challenges could also lead to dual-use solutions that address non-military needs thereby creating broader economic benefit.