IEEE Technology and Society Magazine - September 2023 - 90

Feature
fishermen and generate reports on the status of
their actions, ensuring compliance with labor regulations.
To achieve this, we employ data collection
and reporting systems that gather information on
various aspects of fishing vessels, including location,
catch, and other activities. This information
is crucial in verifying the fishermen's actions and
ensuring their adherence to the labor laws and
regulations established for their protection. Implementing
CCTV, MFVAS, and robust reporting mechanisms
significantly enhances transparency and
accountability within Taiwan's DWF industry. By
promoting sustainable and responsible practices,
these systems contribute to the overall well-being
of the industry. Figure 2 illustrates an overview of
the proposed method.
Our system comprises two main modules: data
collection and labor exploitation analysis. The data
collection module gathers data from the MFVAS
and CCTV recordings from DWF vessels. The labor
exploitation analysis module utilizes the collected
data to generate reports on labor exploitation, which
can be daily, weekly, or monthly. The proposed system
functions as follows.
* The captain records the fisherman's daily or
weekly working hours using the MFVAS.
* The fisherman reviews and approves the
recorded working hours through the MFVAS.
* The recorded working hour details are stored in
the SQLite database on the edge server and subsequently
transferred to the cloud server.
* Government officers can employ statistical
assessment method and fisherman action recognition
techniques to generate labor exploitation
analysis reports daily or weekly.
Regarding the CCTV aspect, the installation of
CCTV cameras on Taiwan's DWF vessels was driven
by the government's commitment to preventing
labor abuse and exploitation. The presence of CCTV
footage serves as crucial evidence to take necessary
legal actions against fishing vessels involved in labor
exploitation. The cameras are strategically positioned
at various angles, capturing footage in open
environments, including challenging conditions like
nighttime and rainy weather. However, the analysis
of such CCTV videos can be complex due to these
environmental factors. Additionally, distinguishing
between individual fishermen becomes difficult due
to their attire, which typically includes raincoats,
rain caps, and rain boots. The storage and memory
requirements for managing vast amounts of CCTV
data are substantial, and video content processing
demands significant computational power.
Mobile face verification application system
The documentation of fisherman's working details
on article poses challenges in analyzing and addressing
labor exploitation. To overcome this, we have
developed the MFVAS using the flutter framework,
which enables the collection of accurate and comprehensive
working details directly from the captain
and fisherman. This ensures greater transparency
Figure 2. Overview of the proposed system.
90
IEEE Technology and Society Magazine
IEEE Technology and Society Magazine - September 2023

Table of Contents for the Digital Edition of IEEE Technology and Society Magazine - September 2023
