Group items tagged

With the development of the marine economy, video surveillance has become an important technical guarantee in the fields of marine engineering, marine public safety, marine supervision, and maritime traffic safety. In video surveillance, maritime object detection (MOD) is one of the most important core technologies. Affected by the size of maritime objects, distance, day and night weather, and changes in sea conditions, MOD faces challenges such as false detection, missed detection, slow detection speed, and low accuracy. However, the existing object detection algorithms usually adopt predefined anchor boxes to search and locate for objects of interest, making it difficult to adapt to maritime objects' complex features, including the varying scale and large aspect ratio difference. Therefore, this paper proposes a maritime object detection algorithm based on the improved convolutional neural network (CNN). Firstly, a differential-evolutionary-based K-means (DK-means) anchor box clustering algorithm is proposed to obtain adaptive anchor boxes to satisfy the maritime object characteristics. Secondly, an adaptive spatial feature fusion (ASFF) module is added in the neck network to enhance multi-scale feature fusion. Finally, focal loss and efficient intersection over union (IoU) loss are adopted to replace the original loss function to improve the network convergence speed. The experimental results on the Singapore maritime dataset show that our proposed algorithm improves the average precision by 7.1%, achieving 72.7%, with a detection speed of 113 frames per second, compared with You Only Look Once v5 small (YOLOv5s). Moreover, compared to other counterparts, it can achieve a better speed-accuracy balance, which is superior and feasible for the complex maritime environment.

Accessing the world's oceans is essential for monitoring and sustainable management of the maritime domain. Difficulty in reaching remote locations has resulted in sparse coverage, undermining our capacity to deter illegal activities and gather data for physical and biological processes. Uncrewed Surface Vessels (USVs) have existed for over two decades and offer the potential to overcome difficulties associated with monitoring and surveillance in remote regions. However, they are not yet an integral component of maritime infrastructure. We analyse 15 years of non-autonomous and semi-autonomous USV-related literature to determine the factors limiting technological diffusion into everyday maritime operations. We systematically categorised over 1,000 USV-related publications to determine how government, academia and industry sectors use USVs and what drives their uptake. We found a striking overlap between these sectors for 11 applications and nine drivers. Low cost was a consistent and central driver for USV uptake across the three sectors. Product 'compatibility' and lack of 'complexity' appear to be major factors limiting USV technological diffusion amongst early adopters. We found that the majority (21 of 27) of commercially available USVs lacked the complexity required for multiple applications in beyond the horizon operations. We argue that the best value for money to advance USV uptake is for designs that offer cross-disciplinary applications and the ability to operate in an unsheltered open ocean without an escort or mothership. The benefits from this technological advancement can excel under existing collaborative governance frameworks and are most significant for remote and developing maritime nations.

India's recent announcement that it will deploy two of its new Boeing P-8 maritime surveillance and strike aircraft to the Andaman & Nicobar Islands.

Sri Lanka donates 2 patrol vessels to Seychelles for maritime surveillance.

Eyes on the sea: companies compete for Australian maritime surveillance contract.

'Chinese presence in WPS won't deter Philippines maritime patrol'.

Malaysia: Maritime crime down by 45%.

India warships sent to strategic Gulf waters: navy.

A European project is coming close to the validation of a prototype of 'Passive bistatic radar' (PBR) technology based on Galileo transmissions. Once finalised, the new system could help relevant authorities to assure better maritime surveillance, detecting and localising, even of non-indexed ships.

The COVID-19 pandemic and its lock-down measures have resulted in periods of reduced human activity, known as anthropause. While this period was expected to be favorable for the marine ecosystem, due to a probable reduction of pollution, shipping traffic, industrial activity and fishing pressure, negative counterparts such as reduced fisheries surveillance could counterbalance these positive effects. Simultaneously, on-land pressure due to human disturbance and tourism should have drastically decreased, potentially benefiting land-breeding marine animals such as seabirds. We analyzed 11 breeding seasons of data on several biological parameters of little penguins from a popular tourist attraction at Phillip Island, Australia. We investigated the impact of anthropogenic activities on penguin behavior during the breeding season measured by (1) distribution at sea, (2) colony attendance, (3) isotopic niche (4) chick meal mass, and (5) offspring investment against shipping traffic and number of tourists. The 2020 lock-downs resulted in a near absence of tourists visiting the Penguin Parade®, which was otherwise visited by 800,000+ visitors on average per breeding season. However, our long-term analysis showed no effect of the presence of visitors on little penguins' activities. Surprisingly, the anthropause did not trigger any changes in maritime traffic intensity and distribution in the region. We found inter- and intra-annual variations for most parameters, we detected a negative effect of marine traffic on the foraging efficiency. Our results suggest that environmental variations have a greater influence on the breeding behavior of little penguins compared to short-term anthropause events. Our long-term dataset was key to test whether changes in anthropogenic activities affected the wildlife during the COVID-19 pandemic.

NIMASA, Air Force showcases aircraft to monitor crime-infested waters.

Once migrants on Mediterranean were saved by naval patrols. Now they have to watch as drones fly over.