Drones
Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models
Feng, Tongtong, Li, Qing, Wang, Xin, Wang, Mingzi, Li, Guangyao, Zhu, Wenwu
Cross-view geo-localization in GNSS-denied environments aims to determine an unknown location by matching drone-view images with the correct geo-tagged satellite-view images from a large gallery. Recent research shows that learning discriminative image representations under specific weather conditions can significantly enhance performance. However, the frequent occurrence of unseen extreme weather conditions hinders progress. This paper introduces MCGF, a Multi-weather Cross-view Geo-localization Framework designed to dynamically adapt to unseen weather conditions. MCGF establishes a joint optimization between image restoration and geo-localization using denoising diffusion models. For image restoration, MCGF incorporates a shared encoder and a lightweight restoration module to help the backbone eliminate weather-specific information. For geo-localization, MCGF uses EVA-02 as a backbone for feature extraction, with cross-entropy loss for training and cosine distance for testing. Extensive experiments on University160k-WX demonstrate that MCGF achieves competitive results for geo-localization in varying weather conditions.
U2UData: A Large-scale Cooperative Perception Dataset for Swarm UAVs Autonomous Flight
Feng, Tongtong, Wang, Xin, Han, Feilin, Zhang, Leping, Zhu, Wenwu
Modern perception systems for autonomous flight are sensitive to occlusion and have limited long-range capability, which is a key bottleneck in improving low-altitude economic task performance. Recent research has shown that the UAV-to-UAV (U2U) cooperative perception system has great potential to revolutionize the autonomous flight industry. However, the lack of a large-scale dataset is hindering progress in this area. This paper presents U2UData, the first large-scale cooperative perception dataset for swarm UAVs autonomous flight. The dataset was collected by three UAVs flying autonomously in the U2USim, covering a 9 km$^2$ flight area. It comprises 315K LiDAR frames, 945K RGB and depth frames, and 2.41M annotated 3D bounding boxes for 3 classes. It also includes brightness, temperature, humidity, smoke, and airflow values covering all flight routes. U2USim is the first real-world mapping swarm UAVs simulation environment. It takes Yunnan Province as the prototype and includes 4 terrains, 7 weather conditions, and 8 sensor types. U2UData introduces two perception tasks: cooperative 3D object detection and cooperative 3D object tracking. This paper provides comprehensive benchmarks of recent cooperative perception algorithms on these tasks.
Russia, Ukraine trade drone attacks in renewed escalation
Russia has launched several strikes across Ukraine, killing at least five people and wounding several, in an attack that appeared to target energy infrastructure. Ukraine also launched a drone attack on Russia's central region of Saratov, injuring four. The exchange began around midnight on Sunday and continued beyond daybreak on Monday. Ukraine's air force reported multiple groups of Russian drones moving towards its eastern, northern, southern, and central regions, followed by numerous cruise and ballistic missiles. Authorities in at least six Ukrainian regions said blasts had been heard.
Twenty-one civilians killed in Mali drone strikes: Separatist group
At least 21 people, including 11 children, have been killed in drone attacks in the town of Tinzaouaten in northern Mali. A spokesperson for the coalition of Tuareg-majority groups fighting for independence in northern Mali said on Monday that the drones hit a pharmacy and a group of people, leaving dozens wounded. Mali's army confirmed the drone attacks on national television, saying the "precision strikes targeted terrorists". Tinzaouaten has witnessed air attacks before and as recently as July when the Tuareg-led groups claimed to have killed a large number of Malian soldiers and Russian Wagner Group mercenaries. The separatists said they killed at least 47 soldiers and 84 Wagner mercenaries in the July attacks, but the army did not confirm that death toll.
Drone footage shows firefighters tackling Dagenham blaze
Two people have been taken to hospital after a fire at a building partly used as a block of flats in Dagenham, east London. Over 100 residents were moved to safety after the building in Freshwater Road, Dagenham, started burning in the early hours of Tuesday morning. The scaffolding as well as parts of the building up to the sixth floor and the roof were ablaze, the London Fire Brigade (LFB) said. The cause of the fire is not yet known, it added. You can read more on this story here.
North Korean leader Kim Jong Un oversees suicide drone tests
North Korean leader Kim Jong Un has supervised a test of domestically-developed attack drones, state media KCNA reported. Photos published by North Korean media on Monday showed a white drone with X-shaped tails and wings crashing into and destroying a target resembling South Korea's K-2 main battle tank. Kim, who was pictured at a desk surrounded by advisers, has been modernising his country's military and developing its weapons capabilities amid rising tensions with Washington and Seoul. The North Korean leader supervised the test on a visit to the Drone Institute of North Korea's Academy of Defense Science, KCNA said. Kim said that global trends in military technologies and modern combat showed the importance of drones in war and that Pyongyang's military should be equipped with them "as early as possible".
Zelenskyy touts new 'drone missile' as he labels Putin 'sick old man'
President Volodymyr Zelenskyy touted a newly developed Ukrainian "drone missile" on Saturday that he said would take the war back to Russia and scornfully derided Russia's Vladimir Putin as a "sick old man from Red Square." As Ukraine marked 33 years of post-Soviet independence, Zelenskyy said the new weapon, Palianytsia, was faster and more powerful than the domestically made drones that Kyiv has so far used to fight back against Russia, striking its oil refineries and military airfields. "Our enemy will ... know what the Ukrainian way for retaliation is. Worthy, symmetrical, long-ranged," he said.
Authorities in northern Iraq report casualties from Turkish drone strike
Local authorities and news outlets in northern Iraq's semi-autonomous Kurdish region have said that several people were killed in a Turkish drone strike on Friday, including two journalists. In an initial statement on Friday, the regional authorities said that a car belonging to the Kurdistan Workers' Party (PKK) was struck near the city of Sulaymaniyah, killing a senior PKK official, his guard and his driver. However, a later statement by the Kurdistan regional government's Deputy Prime Minister Qubad Talabani said that the attack targeted a group of journalists, two of whom were killed. "They were two women journalists, not members of an armed force to be a threat to the security and stability of any country or region," Talabani said in a statement. Reporters Without Borders (RSF), a press advocacy organisation, also released a statement denouncing the deaths of the two journalists, identified as 27-year-old Hero Baha'uddin and 40-year-old Golestan Tara from Sterk TV.
UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios
Nihal, Ragib Amin, Yen, Benjamin, Itoyama, Katsutoshi, Nakadai, Kazuhiro
Unmanned aerial vehicles (UAVs) have revolutionized search and rescue (SAR) operations, but the lack of specialized human detection datasets for training machine learning models poses a significant challenge. To address this gap, this paper introduces the Combination to Application (C2A) dataset, synthesized by overlaying human poses onto UAV-captured disaster scenes. Through extensive experimentation with state-of-the-art detection models, we demonstrate that models fine-tuned on the C2A dataset exhibit substantial performance improvements compared to those pre-trained on generic aerial datasets. Furthermore, we highlight the importance of combining the C2A dataset with general human datasets to achieve optimal performance and generalization across various scenarios. This points out the crucial need for a tailored dataset to enhance the effectiveness of SAR operations. Our contributions also include developing dataset creation pipeline and integrating diverse human poses and disaster scenes information to assess the severity of disaster scenarios. Our findings advocate for future developments, to ensure that SAR operations benefit from the most realistic and effective AI-assisted interventions possible.
What is Israel doing to Palestinians in Tulkarem?
Israel killed three Palestinians in a drone strike on Thursday in Tulkarem, a city and refugee camp in the occupied West Bank. That was during an Israeli raid – a near-daily occurrence in the West Bank – on the Tulkarem refugee camp, during which Israeli troops clashed with fighters from the Qassam Brigades, the military wing of Hamas, according to fighters in the city. Here's all you need to know about Israeli raids on Tulkarem: News reports say Israeli soldiers were deployed on rooftops and sent bulldozers into the camp to destroy large residential areas. Israel also reportedly set fire to people's homes and prevented local relief workers from putting the fires out. Experts say Israel's tactics during its raids appear to be part of a broader doctrine to collectively punish the population, ostensibly because pockets of armed resistance are fighting back against Israel's ever-entrenching occupation. Israel claims that it is conducting "counter-terrorism" operations.