Efficient road detection and tracking for unmanned aerial vehicle

Abstract - An unmanned aerial vehicle (UAV) has many applications in a variety of fields. Detection and tracking of a specific road in UAV videos play an important role in automatic UAV navigation, traffic monitoring, and ground–vehicle tracking, and also is very helpful for constructing road networks for modeling and simulation. In this paper, an efficient road detection and tracking framework in UAV videos is proposed. In particular, a graph-cut–based detection approach is given to accurately extract a specified road region during the initialization stage and in the middle of tracking process, and a fast homography-based road-tracking scheme is developed to automatically track road areas. The high efficiency of our framework is attributed to two aspects: the road detection is performed only when it is necessary and most work in locating the road is rapidly done via very fast homography-based tracking. Experiments are conducted on UAV videos of real road scenes we captured and downloaded from the Internet. The promising results indicate the effectiveness of our proposed framework, with the precision of 98.4% and processing 34 frames per second for 1046 x 595 videos on average.

Efficient and accurate set-based registration of time-separated aerial images

This paper addresses the task of time-separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change under illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several major novelties (i) unlike previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how image space local, pair-wise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed; (iv) lastly, we introduce a new and, to the best of our knowledge, the only data corpus suitable for the evaluation of set-based aerial image registration algorithms. Using this data set, we demonstrate (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task and (ii) that the increase in the number of available images in a set consistently reduces the average registration error, with a major difference already for a single additional image.

Adaptive robust control of 6-DOF autonomous aerial vehicles

The thesis focused on development of an auto-pilot system for UAV’s and small fixed wing aircraft for use in hazardous flight conditions, such as severe weather. This led to development of a mathematical algorithm that unbinds the flight systems from coupling effects which can adaptively changed to the environment.

Groupwise registration of aerial images

This paper addresses the task of time separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change in illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several novelties: (i) unlike all previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how local, pairwise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed. We demonstrate: (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task; and (ii) that the increase in the number of available images in a set consistently reduces the average registration error.

A new perspective of storm bite on sandy beaches using unmanned aerial vehicles

Aerial imagery collected before and after major storm events is ideal for the assessment of coastal landscape change driven by individual high-magnitude events. Using traditional satellite sensors and manned aerial systems can be challenging due to issues related to cloud cover, mobilization expenses and resolution. Rapid advances in unmanned aerial vehicle (UAV) technology allow for the cost-effective collection of aerial imagery and topography at centimetre resolution suitable for assessing change in coastal ecosystems. In this study we demonstrate the utility of UAV-based photogrammetry to quantify storm-driven sediment dynamics on a sandy beach on the open-coast shoreline of Victoria, Australia. UAV-based aerial photography was collected before and after a major storm event. High-resolution (< 5 cm) aerial imagery and digital surface models were acquired and change-detection techniques were applied to quantify changes in the beachface. An average beach erosion of 12.24 m3/m with a maximum of 28.05 m3/m was observed, and the volume of sand cut from the beachface and retreat of the foredune are clearly illustrated. Following the storm event, erosion was estimated at 7259.94 ± 503.69 m3 along 550 m of beach. By combining the aerial imagery and derived topographic datasets we demonstrate the advantage of UAV-based photogrammetry techniques for rapid high-resolution data collection in semi-remote locations. Its utility in setting unlimited virtual vantage points is also illustrated and the valuable perspective it provides for tracking landscape change discussed.

Aerial line transect survey to estimate abundance of marsh deer (Blastocerus dichotomus) (Illiger, 1815)

A população de cervo-do-pantanal (Blastocerus dichotomus) está drasticamente reduzida no Brasil. O nosso objetivo foi o de estimar a abundância do cervo-do-pantanal na bacia do Rio Paraná e discutir a metodologia aplicada. Os resultados darão suporte para uma análise do impacto do enchimento da represa de Porto Primavera sobre essa população. Sessenta e nove animais foram registrados através de sobrevôo utilizando-se a metodologia de transecção linear com amostragem das distâncias. Os dados não corrigidos resultaram em uma densidade estimada de 0,0035ind/ha e uma população de 636 indivíduos. A correção de g para os animais que não foram vistos apresentou uma densidade de 0,0049 ind/ha e uma abundância de 896 (CV=0,27) indivíduos. A metodologia foi aplicada com sucesso na estimativa de cervo-do-pantanal. Esse resultado é importante para avaliarmos a população do cervo-do-pantanal na área e para futuramente analisarmos o impacto do enchimento da represa.

Anti-leishmanial effects of purified compounds from aerial parts of Baccharis uncinella C. DC. (Asteraceae)

Species of Baccharis exhibit antibiotic, antiseptic, wound-healing, and anti-protozoal properties, and have been used in the traditional medicine of South America for the treatment of several diseases. In the present work, the fractionation of EtOH extract from aerial parts of Baccharis uncinella indicated that the isolated compounds caffeic acid and pectolinaringenin showed inhibitory activity against Leishmania (L.) amazonensis and Leishmania (V.) braziliensis promastigotes, respectively. Moreover, amastigote forms of both species were highly sensible to the fraction composed by oleanolic + ursolic acids and pectolinaringenin. Caffeic acid also inhibited amastigote forms of L. (L.) amazonensis, but this effect was weak in L. (V.) braziliensis amastigotes. The treatment of infected macrophages with these compounds did not alter the levels of nitrates, indicating a direct effect of the compounds on amastigote stages. The results presented herein suggest that the active components from B. uncinella can be important to the design of new drugs against American tegumentar leishmaniases.

Evaluation of anti-inflammatory activity of derivatives from aerial parts of Baccharis uncinella

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

The breathing pattern and the ventilatory response to aquatic and aerial hypoxia and hypercarbia in the frog Pipa carvalhoi

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Systems of aerial spraying for soybean rust control

A ferrugem asiática da soja, causada pelo fungo Phakopsora pachyrhizi, é considerada a principal doença da soja, e, portanto, a escolha e o uso adequado dos equipamentos de pulverização são essenciais para seu controle. O objetivo deste trabalho foi avaliar o desempenho de diferentes equipamentos de pulverização aérea para o controle curativo da ferrugem da soja, utilizando o fungicida Impact 125 SC (flutriafol) a 0,5 L p c ha-1. Os seguintes tratamentos foram avaliados: atomizador Micronair AU 5000 (10 L ha-1 com óleo e 20 L ha-1 sem óleo na calda); atomizador Stol ARD (10 e 20 L ha-1 ambos com óleo) e o sistema eletrostático Spectrum (10 L ha-1 sem óleo a 64 e 71% de umidade relativa). Utilizou-se óleo de algodão (1,0 L ha-1) acrescido de emulsificante BR 455 a 0,025 L ha-1. O ensaio foi realizado na terceira aplicação de fungicidas, quando foram analisadas quatro repetições nas áreas aplicadas e quatro testemunhas não aplicadas para cada tratamento, avaliando-se a severidade da ferrugem, os depósitos de flutriafol nas folhas de soja e o percentual de redução de ferrugem. A análise dos depósitos nas folhas mostrou que não houve diferenças significativas entre os tratamentos. Os melhores controles da ferrugem foram obtidos com os tratamentos Micronair (10 L ha-1 com óleo), Stol (20 L ha-1 com óleo) e o sistema elestrostático (10 L ha-1) com a menor umidade relativa do ar (64 %).

Water-soluble nutrients in aerial plant parts of peanut and white oat as affected by lime and gypsum application

A calagem e a gessagem influenciam a disponibilidade e a absorção de nutrientes, podendo alterar a quantidade de ácidos orgânicos na parte aérea das culturas. Essas alterações, quantificadas por meio da análise de nutrientes solúveis em água, podem potencializar o efeito da correção do solo, garantindo a sustentabilidade do sistema de semeadura direta. Nesse sentido, objetivou-se avaliar o efeito da aplicação superficial de calcário e gesso no teor de nutientes solúveis em água nos resíduos vegetais das culturas de amendoim e aveia-branca. O experimento foi realizado em Latossolo Vermelho distroférrico em Botucatu (SP), nos anos agrícolas de 2004/2005 e 2005/2006. O delineamento experimental foi em blocos casualizados em esquema de parcelas subdivididas, com quatro repetições, em que as parcelas foram constituídas por doses de calcário, e as subparcelas, pela presença ou ausência da aplicação de gesso. Foi cultivado amendoim no verão e aveia-branca no inverno, em toda a área experimental. Na cultura do amendoim a aplicação de gesso elevou os teores de Ca solúvel em água apenas na primeira safra, em razão do curto período entre a aplicação do produto e a determinação dos teores de nutientes solúveis no extrato vegetal da cultura. A calagem realizada nas culturas de amendoim e aveia-branca elevou os teores solúveis de Ca, Mg, K e não alterou o teor de Cu e reduziu os teores de Zn, Mn e Fe nos dois anos de cultivo. Já a gessagem reduziu os valores da condutividade elétrica do amendoim (2004/2005 e 2005/2006) e da aveia-branca (2004/2005).

Object-Space Road Extraction in Rural Areas Using Stereoscopic Aerial Images

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Three-Dimensional Semiautomatic Road Extraction From a High-Resolution Aerial Image by Dynamic-Programming Optimization in the Object Space

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Mutagenic Activity of Indigofera truxillensis and I. suffruticosa Aerial Parts

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)