Vision sensing for intelligent driving: technical challenges and innovative solutions

Higher Education Press

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Vision sensing for intelligent driving.

view more 

Credit: Xinle Gong, Zhihua Zhong

In the rapidly evolving landscape of automotive technology, vision sensing has emerged as a crucial component for intelligent driving systems. A recent article published in Engineering, titled “Vision Sensing for Intelligent Driving: Technical Challenges and Innovative Solutions,” offers an in-depth analysis of the current state of vision sensing technology and explores potential solutions to enhance its performance.

 

The authors, Xinle Gong from the School of Mechanical Engineering at Beijing Institute of Technology and the School of Vehicle and Mobility at Tsinghua University, along with Zhihua Zhong from the School of Automotive Studies & College of Transportation at Tongji University, delve into the intricacies of vision sensing systems, highlighting their significance in providing critical road condition data and supporting autonomous driving functions. Compared to other in-vehicle perception sensors, vision sensors offer more detailed and comprehensive environmental information, which is essential for intelligent driving decision-making and control.

 

However, the article underscores that automotive-grade cameras face more complex and stringent technical requirements compared to industrial and consumer cameras. These cameras must adapt to variable driving environments, maintain high performance in image processing, hardware robustness, and system integration under different lighting conditions. They also need specialized materials and advanced packaging technologies to ensure good imaging quality even in adverse weather conditions.

 

The authors identify several key challenges faced by vision sensors. For instance, optical lenses are constrained by physical factors such as depth of field, aperture diffraction, and lens size, which affect image quality under varying lighting conditions. Current lenses often fail to preserve critical details in high-contrast scenes, hindering accurate recognition of road conditions and traffic signs. Additionally, wide-angle lenses introduce optical distortion, leading to errors in object recognition and distance estimation. The sharpness of lenses is also limited by the diffraction limit, making it difficult to improve resolution while maintaining miniaturization.

 

CMOS image sensors face challenges related to the trade-off between resolution and frame rate. High spatial resolution increases the number of pixels and the amount of image data collected, but this lengthens data processing time and reduces temporal resolution. Current automotive-grade CMOS sensors typically achieve a dynamic range of only 120–140 dB, which is insufficient to accommodate variations in lighting intensity across all scenarios encountered in intelligent driving. Moreover, increasing resolution reduces pixel size, decreasing saturation charge capacity and further limiting the dynamic range of CMOS image sensors.

 

Image signal processors are also limited in their on-chip and parallel processing capabilities, affecting the speed of image processing, especially for high-resolution and high-frame-rate image data. This limitation directly impacts the real-time response capability of intelligent vehicles. In low-light conditions, sensor noise increases, and the noise reduction and signal enhancement algorithms of current image signal processors require improvement.

 

To address these challenges, the authors propose several innovative solutions. They suggest exploring new high-efficiency photosensitive materials, such as quantum dots and perovskites, to enhance sensing performance. Architectural evolutions inspired by the human visual system can achieve higher dynamic range and ultra-high-speed imaging. Additionally, developing intelligent image processing algorithms based on neuromorphic and quantum computing paradigms can enable real-time, energy-efficient, and robust perception in complex environments.

 

The article provides a comprehensive analysis of the technical challenges faced by in-vehicle vision sensors and offers targeted ideas and recommendations for future research and development. By leveraging new materials, advanced architectural designs, and intelligent algorithms, vision sensing technology can continue to evolve towards greater intelligence, reliability, and integration, ultimately enabling safer, more efficient, and fully autonomous intelligent driving.

 

The paper “Vision Sensing for Intelligent Driving: Technical Challenges and Innovative Solutions” is authored by Xinle Gong, Zhihua Zhong. Full text of the open access paper: https://doi.org/10.1016/j.eng.2025.06.038. For more information about Engineering, visit the website at https://www.sciencedirect.com/journal/engineering.

---

Journal

Engineering

DOI

10.1016/j.eng.2025.06.038 

Article Title

Vision Sensing for Intelligent Driving: Technical Challenges and Innovative Solutions

 

Promoting physical activity can be surprisingly inexpensive – yet impacts are rarely measured

University of Oulu, Finland

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

Physical activity can be increased effectively and at surprisingly low cost at the population level. Simple approaches, such as individually tailored online or print-based advice, can increase physical activity by an average of one hour per week at a cost of less than one euro per participant. At the same time, a new study reveals a significant gap: the costs and real-world impacts of measures promoting physical activity are rarely measured with sufficient accuracy.

A joint study by the University of Oulu and the Department of Sports and Exercise Medicine, Oulu Deaconess Institute Foundation highlights the need for better evaluation of both the effectiveness and the costs of interventions designed to increase physical activity.

The study is an international systematic review examining the effectiveness and cost-effectiveness of population-level physical activity interventions. Researchers screened more than 10,000 studies with the aim of identifying approaches and interventions that had successfully increased physical activity in the population and assessed their economic impacts. Only five studies met the strict inclusion criteria.

“Although many initiatives aim to promote physical activity, their cost-effectiveness is rarely evaluated in a reliable way,” says postdoctoral researcher Anna-Maiju Leinonen.

Costs and impacts are rarely measured

Only studies in which increases in physical activity were demonstrated using reliable measurement methods and where costs were assessed as part of the study design were included in the review. Reliable comparisons require precise and transparent cost calculations for implementing the intervention, as well as, where possible, other costs incurred by society and individuals.

These include, for example, healthcare expenditure as well as productivity costs related to sickness absence and work disability. In addition, physical activity should be measured using validated questionnaires or wearable activity monitors.

The studies included in the review were conducted in Europe, the United States and Australia. They focused mainly on adults and particularly on physically inactive groups.

According to the results, the most cost-effective interventions were simple and low-resource measures, such as printed or web-based advice tailored individually using computer algorithms to encourage people to increase their physical activity. In these interventions, physical activity increased modestly but at relatively low cost per participant.

By contrast, more expensive and complex programmes were less cost-effective in this dataset. The study highlights that promoting physical activity at the population level does not necessarily require large investments or complex programmes.

Health benefits appear slowly

The health benefits of physical activity, such as a reduced risk of chronic diseases and improved work ability, often emerge only over a longer period. However, the follow-up period in the studies included in the review was only one to two years.

During this time, no significant changes were observed in health-related costs or quality of life. According to the researchers, such a short follow-up period is insufficient to demonstrate the real long-term economic benefits of increased physical activity.

“If physical activity can be increased at low cost, it is not only a matter of public health but also of economic sustainability. The key question is not only how to get people moving, but how to do so in a smart and effective way,” Leinonen summarises.

The researchers emphasise that more high-quality and long-term studies are needed in the future in which costs and impacts are assessed systematically and using consistent methods. Only then can limited resources be directed to the measures that achieve the greatest possible health and societal benefits.

In particular, stronger research evidence is needed on the cost-effectiveness of interventions aimed at increasing physical activity among children and young people.

The study has been published in the journal Preventive Medicine: Anna-Maiju Leinonen, Sanna Huikari, Mikko Kärmeniemi, Jaana T. Kari, Raija Korpelainen, Urho M. Kujala, Ding Ding, Marjukka Nurkkala, Economically viable population-based interventions to promote physical activity behavior based on a systematic review, Preventive Medicine, Volume 206, 2026.

 

---

Journal

Preventive Medicine

DOI

10.1016/j.ypmed.2026.108542 

Article Title

Economically viable population-based interventions to promote physical activity behavior based on a systematic review

 

Housing displacement, employment disruption, and mental health after the 2023 Maui wildfires

JAMA Psychiatry

About The Study:

 In this cross-sectional study, wildfire exposure and its socioeconomic consequences were associated with graded increases in psychological distress extending beyond the burn zone. These findings highlight the importance of integrating mental health care, housing stability, and economic recovery as central pillars of disaster response and climate resilience strategies.

 

Corresponding Author: To contact the corresponding author, Ruben Juarez, PhD, email rubenj@hawaii.edu.

To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/

(10.1001/jamapsychiatry.2026.0044)

Editor’s Note: Please see the article for additional information, including other authors, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

#  #  #

Embed this link to provide your readers free access to the full-text article 

 https://jamanetwork.com/journals/jamapsychiatry/fullarticle/10.1001/jamapsychiatry.2026.0044?guestAccessKey=d3d1fa29-f6d4-44f9-b62b-93871d7889e2&utm_source=for_the_media&utm_medium=referral&utm_campaign=ftm_links&utm_content=tfl&utm_term=031126

---

Journal

JAMA Psychiatry

 

Pew awards fellowships to seven scientists advancing marine conservation

Leading researchers join esteemed global community of fellows

Pew Charitable Trusts

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

PHILADELPHIA— The global ocean faces major threats—from illegal fishing to vanishing coastal habitats to plastic pollution. Now, a new cohort of scientists will work to bridge the knowledge gaps hindering effective ocean protections.

The Pew Charitable Trusts announced today that seven fellows—based in Australia, the United States, Canada, Japan, and Thailand—will receive $150,000 grants over three years to pursue conservation-focused research aimed at strengthening ocean health and the communities that depend on it. Their work includes tracing illegal and unreported fisheries with advanced genetic techniques, improving reef restoration in Southeast Asia, mapping climate resilient kelp forests, testing local-based incentives for marine conservation, rethinking fisheries governance in East Asia, analyzing the impacts of harmful algal blooms, and developing open-source technology to classify nanoplastic pollution.

This year’s fellows’ cohort also includes the first recipient of the Pew-Gerstner Fellowship in Ocean Plastics Research, which supports research on solutions to marine plastic pollution; and the second recipient of the Pew-Hoover Fellowship in Marine and Biomedical Science, which fosters innovative research at the intersection of the two fields.

“These fellows are tackling some of the ocean’s toughest challenges with creativity and immense dedication,” said Leo Curran, project director for the Pew Fellows Program in Marine Conservation. “Their work shows what’s possible when science, technology, and communities come together to protect our seas.”

The 2026 fellows join a distinguished community of more than 200 Pew marine fellow alumni dedicated to advancing ocean science and promoting the sustainable use of marine resources. The Pew Fellows Program in Marine Conservation supports midcareer scientists and other experts selected by an international panel of leaders in marine science and conservation. Alumni form an active community that promotes collaboration and knowledge sharing worldwide.

 “Seeing these scientists turn their ideas into action is what excites me most,” said Angela Bednarek, Pew’s director of scientific advancement. “They’re exploring new approaches, testing innovative tools, and working closely with communities and policymakers, bringing research to life in ways that could shape how we care for the oceans.”

The 2026 fellows are:

Suchana Apple Chavanich, Ph.D.
Chulalongkorn University, Thailand
Suchana Apple Chavanich will develop and apply innovative methods to advance reef restoration in Southeast Asia, a region with some of the world’s richest coral diversity. Working in Thailand, Chavanich will refine techniques for producing new corals through sexual propagation and banking frozen coral sperm and eggs—critical methods for preserving the genetic health of restored populations.

Andrés Cisneros-Montemayor, Ph.D.
Simon Fraser University, Canada
Andrés Cisneros-Montemayor will develop a replicable framework to identify the social connections that shape markets in the ocean economy, facilitating the design and implementation of local-scale incentives for conservation. Working with three fishing communities in Sonora, Mexico, Cisneros-Montemayor will apply this framework, conducting field interviews and community engagement workshops to map and understand the layered interactions that influence economic decision-making.

Win Cowger, Ph.D.
Pew-Gerstner Fellow in Ocean Plastics Research
Moore Institute for Plastic Pollution Research, United States
Win Cowger will enhance the capabilities of Open Specy, an open-source tool he developed to help researchers worldwide classify and analyze different types of plastic pollution. He will build a robust reference library and develop new algorithms to improve the identification of nanoplastics, small microplastics, and plastic leachates in the marine environment.

Nur Arafeh-Dalmau, Ph.D.
University of Queensland, Australia
Nur Arafeh-Dalmau will collaborate with partners in California, Mexico, Peru, and Argentina to identify and map resilient kelp forest ecosystems. Using satellite imagery, ecological surveys, and environmental DNA, Arafeh-Dalmau will analyze biodiversity patterns in persistent kelp forests and test their resilience to marine heat waves.

Matthew Gribble, Ph.D.
Pew-Hoover Fellow in Marine and Biomedical Science
University of California, San Francisco, United States
Matthew Gribble will apply an advanced statistical technique called a hidden Markov model to better understand the dynamics of toxin-producing algal blooms. His work will focus on southeast Alaska, where Alaska Native communities have been repeatedly affected by harmful algal blooms, and Andalucia, Spain. Gribble will determine how often areas have been exposed to algal blooms in the past, supporting insights into the health effects of harmful algal toxin exposure.

Shaili Johri, Ph.D.
Stanford University, United States
Shaili Johri will use advanced genetic tools to strengthen seafood traceability and combat illegal fishing. By analyzing fine-scale differences in individual animals’ DNA, her research will help pinpoint the geographic origins of traded species. Focusing on reef sharks, Johri will develop low-cost, rapid, and accurate genetic and visual identification methods to identify shark fishing hot spots across the Western Indian Ocean and detect instances of illegal fishing.

Namhee Kwon, Ph.D.
Kansai University, Japan
Namhee Kwon will analyze the effectiveness and limitations of existing agreements in managing shared fish stocks, with the goal of identifying institutional and legal reforms that are both politically viable and ecologically sustainable. Focusing on agreements among South Korea, Japan, and China, Kwon will examine the legal architecture of each agreement, obligations under the United Nations Convention on the Law of the Sea, and implementation of these agreements within each country’s domestic system.

 

The complete genome of the golden lancehead reveals how genes responsible for venom toxins evolved

Fundação de Amparo à Pesquisa do Estado de São Paulo

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

Approximately 100,000 years ago, a portion of a continental population of around 140,000 individuals likely became isolated on a mountain that now comprises Queimada Grande Island 

view more 

Credit: Daniel Antônio/Agência FAPESP

A research team led by scientists at the Butantan Institute in São Paulo, Brazil, and funded by FAPESP, has completed the most extensive genetic sequencing of a jararaca viper to date. The focus of the study was the genome of the golden lancehead (Bothrops insularis), particularly its venom genes. Since the species shares most of its genes with the other 48 species in the genus, the data serve as a reference for broader studies on the evolution of jararaca vipers and their toxins.

The study was published in the journal Genome Biology and Evolution.

The golden lancehead was described in 1921 as a different species from the one known on the mainland, simply called jararaca (Bothrops jararaca). Isolated on Queimada Grande Island, off the coast of São Paulo, about 100,000 years ago, the population differed from its mainland counterparts to the point of separating into a new species. 

In addition to having yellow skin, the golden lancehead is semi-arboreal and feeds on birds as an adult. Jararacas on the mainland, on the other hand, are dark in color and usually hunt small mammals, such as rats, on the ground. In 2021, B. jararaca became the first Brazilian snake to have its genome sequenced (read more at agencia.fapesp.br/36548).   

“Experimental studies have long shown that the venom of the golden lancehead is more potent in birds than in mammals. We didn’t find major differences in the toxin genes, but it’s likely that some protein or smaller piece of one of them may be enough to make the venom more lethal to birds,” says Pedro Nachtigall, the lead author of the study, which was conducted during his postdoctoral research at the Butantan Institute with a fellowship from FAPESP. 

The genome revealed that the golden lancehead’s venom is rich in enzymes and proteins that cause bleeding and coagulation disorders. It also has the potential to act on other fronts, such as hypotension and tissue damage, which are common to the venoms of jararacas on the continent.

The researchers also noted that variations in the species’ genome do not occur randomly through a process known as genetic drift. On the contrary, the analyses pointed to a high degree of natural selection. 

“Because it’s an isolated population, these changes could be occurring randomly as a result of low genetic variability. That isn’t what we saw. There’s a more specific distribution, a sign that selective pressure exists. This may have been caused by either diet or by the species being restricted to a very small area,” says Inácio Junqueira de Azevedo, a researcher at the Butantan Institute who coordinated the study, which is part of a project supported by FAPESP. 

The entire wild population of golden lanceheads is restricted to Queimada Grande Island, which is 43 hectares in size. The island was formed off the coast of São Paulo after the last glaciation 100,000 years ago, when sea levels rose considerably.

In addition to the complete genome of a male from the island, the study included the less detailed genomes of eight other individuals: seven living in the wild and one part of an ex situ conservation program at the Butantan Institute. By comparing the genomes, researchers can better understand the genetic variability within the species.

Among future applications, the study will serve as a basis for comparing the genome of the wild population with that of the captive population, allowing for an assessment of the genetic health of the latter. Additionally, the genetic profile of the wild population informs conservation policies for the critically endangered golden lancehead. 

Evolution and dating

Another analysis that provided the basis for the study was the transcriptome of four individuals, which is the set of molecules produced by the venom gland. While a doctoral student in the early 2000s, Junqueira de Azevedo conducted the first transcriptomic study of a snake’s venom gland, specifically that of the golden lancehead. At that time, genetic sequencing was still novel, and he received a scholarship from FAPESP. 

The current study expands our knowledge of jararaca venom and could be used in the future for biotechnological applications such as anticoagulant drugs or drugs that lower blood pressure. For example, one such drug, captopril, originated from the venom of the jararaca viper found on the continent.  

“Far beyond finding applications, studies like this help us understand the evolution of venom genes and, in this case, revealed the origin of a toxin subtype from an existing type,” Junqueira de Azevedo explains. 

The complete genome made it possible to reconstruct the species’ demographic history, beginning with an origin population approximately 100,000 years ago. A mathematical model was used to estimate past periods of population decline and the number of individuals expected today. These estimates are based on the mutation rate and the assumption of a new generation of snakes every two years. 

According to the model, approximately 100,000 years ago, a portion of a continental population of around 140,000 individuals likely became isolated on a mountain that now comprises Queimada Grande Island. Analyses show two subsequent severe population declines that coincide with two possible insularization events. One occurred 50,000 years ago, reaching 30,000 snakes, and the other occurred 11,000 years ago when the population fell to 10,000 individuals.

“It’s impossible to know for sure, but there may have been an initial isolation due to rising sea levels, which would have subsequently fallen, allowing that population to come into contact with snakes from the mainland and exchange genes with them. Then, a second rise in sea levels isolated them for good,” says Nachtigall, who completed an internship at Florida State University in the United States during his research.  

A more gradual decline occurred between 10,000 and 5,000 years ago, reaching about 5,000 snakes, which is consistent with the current census of the island, which estimated the current population at between 2,000 and 4,000 golden lanceheads.

“We were able to achieve a genome with very high resolution, which generates a robust database for population, evolutionary, conservation, genomic, and venom studies, to understand both the origins and possible applications of toxins,” Junqueira de Azevedo concludes.

The work also received a grant from FAPESP through the FAPESP Research Program on Biodiversity Characterization, Conservation, Restoration, and Sustainable Use (BIOTA-FAPESP).  

About São Paulo Research Foundation (FAPESP)
The São Paulo Research Foundation (FAPESP) is a public institution with the mission of supporting scientific research in all fields of knowledge by awarding scholarships, fellowships and grants to investigators linked with higher education and research institutions in the State of São Paulo, Brazil. FAPESP is aware that the very best research can only be done by working with the best researchers internationally. Therefore, it has established partnerships with funding agencies, higher education, private companies, and research organizations in other countries known for the quality of their research and has been encouraging scientists funded by its grants to further develop their international collaboration. You can learn more about FAPESP at www.fapesp.br/en and visit FAPESP news agency at www.agencia.fapesp.br/en to keep updated with the latest scientific breakthroughs FAPESP helps achieve through its many programs, awards and research centers. You may also subscribe to FAPESP news agency at http://agencia.fapesp.br/subscribe.

 

 

---

Journal

Genome Biology and Evolution

DOI

10.1093/gbe/evaf243 

Article Title

The Golden Lancehead Genome Reveals Distinct Selective Processes Acting on Venom Genes of an Island Endemic Snake