Greg Nichols covers robotics, AI, and AR/VR for ZDNet. A full-time journalist and author, he writes about tech, travel, crime, and the economy for global media outlets and reports from across the U. There can be little doubt that the FAA is paving the way for a framework governing the widespread operation of commercial drones in the U.S. In advance of a definitive ruling on whether commercial drones can operate beyond visual line of sight (BVLOS), the FAA has been busily granting case-by-case permission to drone operators for exactly that. One recent example, just announced, drone company American Robotics has added seven additional sites of operation approved by the FAA for its automated BVLOS drone technology, the Scout System. American Robotics has 10 operational sights across eight U.S. states.
Rapid urbanisation in Nairobi, Kenya's capital city, has meant there's been huge growth in the number of vehicles on roads. Today, Nairobi is one of the world's most congested cities. Kenya Urban Roads Authority (KURA) Director General Silas Kinoti has said intelligent infrastructure is helping transport networks to become more connected in an attempt to identify ways of improving experience for everyone on the road. Bird's eye view tech aims to unlock Nairobi traffic jams according to @KURAroads Director General @MuriraKinoti who believes that construction of many roads is a milestone yes but not a solution to nerve-racking snarl ups pic.twitter.com/WGHhRk9N3X He said Kenya will be seeking to emulate on their foreign counterparts like Germany to initiate usage of Artificial Intelligence(AI) to optimise traffic light control and reduce the waiting time at an intersection. "There are real world projects around the globe and the applications are continuously expanding. Artificial Intelligence (AI) will be key to help us with the data which would identify patterns that would not have been seen without AI. Through continuous learning, we're able to constantly update the traffic patterns and thus traffic flow. Road Traffic monitoring involves the collection of data describing the characteristic of vehicles and their movement through road networks. Such data may be used for one of these purposes such as law enforcement, congestion and incident detection and increasing road capacity. The roads in Nairobi carry more than 60 per cent of more than two million registered vehicles, resulting in tangles of traffic stretching for miles. Earlier today, KURA top management team inspected the dualling of the Eastern Bypass Project and appreciated the progress achieved. Once the road is complete, traffic jams will be reduced and improve connectivity.@PDUDelivery "KURA being an expert in Intelligent Traffic System (ITS) with an example being Yaya Centre,we will have cameras, signals and censors in all arms of the junctions.
WARNING--Graphic footage: Fox News correspondent Bryan Llenas has the latest on the investigation from Brooklyn, New York, on'Special Report.' New York City may be rolling out new technology and periodic bag checks to prevent future terrorist attacks, according to the mayor. New York City Mayor Eric Adams spoke with MSNBC's "Morning Joe" on Wednesday about the previous day's terror attack on the city's subway system. The mayor touched on the possibility of new technology on public transportation to prevent similar acts in the future. "With the gun detection devices – oftentimes when people hear of'metal detectors,' they immediately think of the airport model," Adams said.
The way we commute may have transformed over time, but the way traffic is managed has not changed. The INRIX Global Traffic Scorecard reports that the world's 20 most congested cities lost between 164 and 210 hours in congestion per capita through 2018. Exponential rise of vehicles in urban cities is the core reason behind congestion. Better public transport is the solution, but along with this, we need to also look at how improving the efficiency of the traffic management can better the scene. Traffic authorities have tried initiatives to transform reactive management into proactive traffic management but have been constrained by network speeds and processing capabilities at the edge.
Artificial Intelligence and deep learning in video analytics are gaining popularity. It has enabled a wide range of industrial applications, including surveillance and public safety, robotics perception, medical intervention, and facial recognition. According to Markets & Markets, the global market for video analytics was valued at USD 5.9 billion in 2021 and is predicted to reach USD 14.9 billion by 2026. Unmanned aerial vehicles (UAVs) have also enabled a wide range of video analytics applications (e.g., aerial surveys) since they provide aerial views of the environment, allowing for collecting aerial photos and processing with deep learning algorithms. Parking analytics is one of these critical smart city applications that uses deep learning and UAVs to collect real-time data and analyze it in order to maximize parking revenue, enhance parking resource allocations, and better manage public space.
Sardar Vallabhbhai Patel International Airport (SVPIA) has introduced an indigenously developed artificial intelligence (AI) based surveillance service, Desk of Goodness, to help flyers through smart detection techniques. Desk of Goodness aims to serve passengers like senior citizens, women with infants, and passengers in need of a wheelchair. This desk is manned by goodness champions equipped with smart tabs, which keep them updated on possible sites where passengers need support. "Sardar Vallabhbhai Patel International Airport continues to improve infrastructure and services to enhance the passenger experience," said Jeet Adani, Director, Adani Airport Holdings. "AI-based video content analytics plays a crucial role in reaching out to flyers in emergencies. Analytics-based learnings will allow us to set new benchmarks in operational intelligence and increasing situational awareness, thereby improving safety, security and efficiency."
The first two generations of cellular--1G/2G--enabled ubiquitous voice connectivity. Even generations introduced services for business customers, and odd generations democratized them for consumers. One main avenue for achieving this is cost reduction.6 Another avenue is radio access with joint communications and sensing.7 New services are envisioned, such as low-altitude air traffic control, detecting, for example, bird migration and adapting drone services accordingly. Every opportunity of improving sensing is an opportunity for spying.
It is usually seen that the traffic on the side of the road where we are traveling is crowded and the opposite side is almost empty but the green signal is given for the same period for every direction without assigning any priority. Caught in one such occasion while traveling for a medical emergency, Deepraj Chowdhary, a B.Tech student from the International Institute of Information Technology-Naya Raipur hit upon an idea to use artificial intelligence to speed up traffic more smartly. Christened as Smart Traffic Signal Management System for Roadways, Chowdhary has used artificial intelligence in python programming language and written algorithms to give more green signals for the direction which has the highest density of vehicles. Currently, the waiting duration for vehicles at traffic signals is equally divided irrespective of the density though traffic police can adjust it manually. Moreover, almost all the major traffic signals are attached with cameras that send live feed to the control room.
Pangiam, in collaboration with Google Cloud, has announced details of Project DARTMOUTH, an initiative to transform airport security operations by looking for threats concealed within baggage and other shipments at the airport. This technology will be tested within the security facilities of AGS Airport Ltd, owners and operators of Aberdeen, Glasgow, and Southampton Airports in the UK. Project DARTMOUTH is intended to make air travel safer by integrating AI into airport baggage security and screening operations. The technology will in the first instance be focused on rapidly identifying potential threats in baggage, providing increased throughput at security checkpoints, addressing critical friction points in air travel as well as supporting security teams. In later phases the technology will scale to help tackle other pressure points in security and wider airport operations.
As an important task for the management of bike sharing systems, accurate forecast of travel demand could facilitate dispatch and relocation of bicycles to improve user satisfaction. In recent years, many deep learning algorithms have been introduced to improve bicycle usage forecast. A typical practice is to integrate convolutional (CNN) and recurrent neural network (RNN) to capture spatial-temporal dependency in historical travel demand. For typical CNN, the convolution operation is conducted through a kernel that moves across a "matrix-format" city to extract features over spatially adjacent urban areas. This practice assumes that areas close to each other could provide useful information that improves prediction accuracy. However, bicycle usage in neighboring areas might not always be similar, given spatial variations in built environment characteristics and travel behavior that affect cycling activities. Yet, areas that are far apart can be relatively more similar in temporal usage patterns. To utilize the hidden linkage among these distant urban areas, the study proposes an irregular convolutional Long-Short Term Memory model (IrConv+LSTM) to improve short-term bike sharing demand forecast. The model modifies traditional CNN with irregular convolutional architecture to extract dependency among "semantic neighbors". The proposed model is evaluated with a set of benchmark models in five study sites, which include one dockless bike sharing system in Singapore, and four station-based systems in Chicago, Washington, D.C., New York, and London. We find that IrConv+LSTM outperforms other benchmark models in the five cities. The model also achieves superior performance in areas with varying levels of bicycle usage and during peak periods. The findings suggest that "thinking beyond spatial neighbors" can further improve short-term travel demand prediction of urban bike sharing systems.