Initial Detections Research Articles

Long-term follow-up observations of extreme coronal line emitting galaxies

ABSTRACT We present new spectroscopic and photometric follow-up observations of the known sample of extreme coronal line-emitting galaxies (ECLEs) identified in the Sloan Digital Sky Survey (SDSS). With these new data, observations of the ECLE sample now span a period of two decades following their initial SDSS detections. We confirm the non-recurrence of the iron coronal line signatures in five of the seven objects, further supporting their identification as the transient light echoes of tidal disruption events (TDEs). Photometric observations of these objects in optical bands show little overall evolution. In contrast, mid-infrared (MIR) observations show ongoing long-term declines consistent with power-law decay. The remaining two objects had been classified as active galactic nuclei (AGNs) with unusually strong coronal lines rather than being TDE related, given the persistence of the coronal lines in earlier follow-up spectra. We confirm this classification, with our spectra continuing to show the presence of strong, unchanged coronal line features and AGN-like MIR colours and behaviour. We have constructed spectral templates of both subtypes of ECLE to aid in distinguishing the likely origin of newly discovered ECLEs. We highlight the need for higher cadence, and more rapid, follow-up observations of such objects to better constrain their properties and evolution. We also discuss the relationships between ECLEs, TDEs, and other identified transients having significant MIR variability.

A Novel Framework for Image Matching and Stitching for Moving Car Inspection under Illumination Challenges.

Vehicle exterior inspection is a critical operation for identifying defects and ensuring the overall safety and integrity of vehicles. Visual-based inspection of moving objects, such as vehicles within dynamic environments abounding with reflections, presents significant challenges, especially when time and accuracy are of paramount importance. Conventional exterior inspections of vehicles require substantial labor, which is both costly and prone to errors. Recent advancements in deep learning have reduced labor work by enabling the use of segmentation algorithms for defect detection and description based on simple RGB camera acquisitions. Nonetheless, these processes struggle with issues of image orientation leading to difficulties in accurately differentiating between detected defects. This results in numerous false positives and additional labor effort. Estimating image poses enables precise localization of vehicle damages within a unified 3D reference system, following initial detections in the 2D imagery. A primary challenge in this field is the extraction of distinctive features and the establishment of accurate correspondences between them, a task that typical image matching techniques struggle to address for highly reflective moving objects. In this study, we introduce an innovative end-to-end pipeline tailored for efficient image matching and stitching, specifically addressing the challenges posed by moving objects in static uncalibrated camera setups. Extracting features from moving objects with strong reflections presents significant difficulties, beyond the capabilities of current image matching algorithms. To tackle this, we introduce a novel filtering scheme that can be applied to every image matching process, provided that the input features are sufficient. A critical aspect of this module involves the exclusion of points located in the background, effectively distinguishing them from points that pertain to the vehicle itself. This is essential for accurate feature extraction and subsequent analysis. Finally, we generate a high-quality image mosaic by employing a series of sequential stereo-rectified pairs.

Identification of Rare Multiple Core‐Mantle Boundary Reflections PmKP Up To P7KP With Deep Learning

AbstractThe core‐mantle boundary (CMB) marks the most dramatic changes in physical properties within the Earth, and plays a critical role in the understanding of the Earth's dynamics. PmKP waves are seismic phases that reflect (m − 1) times under the CMB and are useful for studying the complex CMB structure. We present an automated workflow for detecting PmKP phases using multi‐station records from global seismic stations. We employ a novel sampling method to extract PmKP waveforms into a 2‐D matrix. Two deep neural networks are then utilized for initial phase detections and subsequent slowness validations. Numerous PmKPab (3 ≤ m ≤ 7) and their CMB diffracted signals were identified for deep earthquakes (magnitude >6) occurred from 2000 to 2020, including diffracted P7KPab waves with diffraction lengths of nearly 20°. Our approach significantly improves the efficiency of PmKP phase identification and holds the capability to detect other weak core phases, such as PKiKP.

Optimized instance segmentation by super-resolution and maximal clique generation

The rise of surveillance systems has led to exponential growth in collected data, enabling several advances in Deep Learning to exploit them and automate tasks for autonomous systems. Vehicle detection is a crucial task in the fields of Intelligent Vehicle Systems and Intelligent Transport systems, making it possible to control traffic density or detect accidents and potential risks. This paper presents an optimal meta-method that can be applied to any instant segmentation model, such as Mask R-CNN or YOLACT++. Using the initial detections obtained by these models and super-resolution, an optimized re-inference is performed, allowing the detection of elements not identified a priori and improving the quality of the rest of the detections. The direct application of super-resolution is limited because instance segmentation models process images according to a fixed dimension. Therefore, in cases where the super-resolved images exceed this fixed size, the model will rescale them again, thus losing the desired effect. The advantages of this meta-method lie mainly in the fact that it is not required to modify the model architecture or re-train it. Regardless of the size of the images given as input, super-resolved areas that fit the defined dimension of the object segmentation model will be generated. After applying our proposal, experiments show an improvement of up to 8.1% for the YOLACT++ model used in the Jena sequence of the CityScapes dataset.

Epidemic versus endemic West Nile virus dead bird surveillance in California: Changes in sensitivity and focus.

Since 2003, the California West Nile virus (WNV) dead bird surveillance program (DBSP) has monitored publicly reported dead birds for WNV surveillance and response. In the current paper, we compared DBSP data from early epidemic years (2004-2006) with recent endemic years (2018-2020), with a focus on specimen collection criteria, county report incidence, bird species selection, WNV prevalence in dead birds, and utility of the DBSP as an early environmental indicator of WNV. Although fewer agencies collected dead birds in recent years, most vector control agencies with consistent WNV activity continued to use dead birds as a surveillance tool, with streamlined operations enhancing efficiency. The number of dead bird reports was approximately ten times greater during 2004-2006 compared to 2018-2020, with reports from the Central Valley and portions of Southern California decreasing substantially in recent years; reports from the San Francisco Bay Area decreased less dramatically. Seven of ten counties with high numbers of dead bird reports were also high human WNV case burden areas. Dead corvid, sparrow, and quail reports decreased the most compared to other bird species reports. West Nile virus positive dead birds were the most frequent first indicators of WNV activity by county in 2004-2006, followed by positive mosquitoes; in contrast, during 2018-2020 mosquitoes were the most frequent first indicators followed by dead birds, and initial environmental WNV detections occurred later in the season during 2018-2020. Evidence for WNV impacts on avian populations and susceptibility are discussed. Although patterns of dead bird reports and WNV prevalence in tested dead birds have changed, dead birds have endured as a useful element within our multi-faceted WNV surveillance program.

A roadmap for ladybird conservation and recovery.

Ladybirds (Coleoptera: Coccinellidae) provide services that are critical to food production, and they fulfill an ecological role as a food source for predators. The richness, abundance, and distribution of ladybirds, however, are compromised by many anthropogenic threats. Meanwhile, a lack of knowledge of the conservation status of most species and the factors driving their population dynamics hinders the development and implementation of conservation strategies for ladybirds. We conducted a review of the literature on the ecology, diversity, and conservation of ladybirds to identify their key ecological threats. Ladybird populations are most affected by climate factors, landscape composition, and biological invasions. We suggest mitigating actions for ladybird conservation and recovery. Short-term actions include citizen science programs and education, protective measures for habitat recovery and threatened species, prevention of the introduction of non-native species, and the maintenance and restoration of natural areas and landscape heterogeneity. Mid-term actions involve the analysis of data from monitoring programs and insect collections to disentangle the effect of different threats to ladybird populations, understand habitat use by taxa on which there is limited knowledge, and quantify temporal trends of abundance, diversity, and biomass along a management-intensity gradient. Long-term actions include the development of a worldwide monitoring program based on standardized sampling to fill data gaps, increase explanatory power, streamline analyses, and facilitate global collaborations.

Using a mechanistic framework to model the density of an aquatic parasite Ceratonova shasta.

Ceratonova shasta is a myxozoan parasite endemic to the Pacific Northwest of North America that is linked to low survival rates of juvenile salmonids in some watersheds such as the Klamath River basin. The density of C. shasta actinospores in the water column is typically highest in the spring (March–June), and directly influences infection rates for outmigrating juvenile salmonids. Current management approaches require quantities of C. shasta density to assess disease risk and estimate survival of juvenile salmonids. Therefore, we developed a model to simulate the density of waterborne C. shasta actinospores using a mechanistic framework based on abiotic drivers and informed by empirical data. The model quantified factors that describe the key features of parasite abundance during the period of juvenile salmon outmigration, including the week of initial detection (onset), seasonal pattern of spore density, and peak density of C. shasta. Spore onset was simulated by a bio-physical degree-day model using the timing of adult salmon spawning and accumulation of thermal units for parasite development. Normalized spore density was simulated by a quadratic regression model based on a parabolic thermal response with river water temperature. Peak spore density was simulated based on retained explanatory variables in a generalized linear model that included the prevalence of infection in hatchery-origin Chinook juveniles the previous year and the occurrence of flushing flows (≥171 m3/s). The final model performed well, closely matched the initial detections (onset) of spores, and explained inter-annual variations for most water years. Our C. shasta model has direct applications as a management tool to assess the impact of proposed flow regimes on the parasite, and it can be used for projecting the effects of alternative water management scenarios on disease-induced mortality of juvenile salmonids such as with an altered water temperature regime or with dam removal.

Automated Seismo-Volcanic Event Detection Applied to Stromboli (Italy)

Many active volcanoes exhibit Strombolian activity, which is typically characterized by relatively frequent mild volcanic explosions and also by rare and much more destructive major explosions and paroxysms. Detailed analyses of past major and minor events can help to understand the eruptive behavior of volcanoes and the underlying physical and chemical processes. Catalogs of these eruptions and, specifically, seismo-volcanic events may be generated using continuous seismic recordings at stations in the proximity of volcanoes. However, in many cases, the analysis of the recordings relies heavily on the manual picking of events by human experts. Recently developed Machine Learning-based approaches require large training data sets which may not be available a priori. Here, we propose an alternative user-friendly, time-saving, automated approach labelled as: the Adaptive-Window Volcanic Event Selection Analysis Module (AWESAM). This strategy of creating seismo-volcanic event catalogs consists of three main steps: 1) identification of potential volcanic events based on squared ground-velocity amplitudes, an adaptive MaxFilter, and a prominence threshold. 2) catalog consolidation by comparing and verifying the initial detections based on recordings from two different seismic stations. 3) identification and exclusion of signals from regional tectonic earthquakes. The strength of the python package is the reliable detection of very small and frequent events as well as major explosions and paroxysms. Here, it is applied to publicly accessible continuous seismic recordings from two almost equidistant stations at Stromboli volcano in Italy. We tested AWESAM by comparison with a hand-picked catalog and found that around 95% of the seismo-volcanic events with a signal-to-noise ratio above three are detected. In a first application, we derive a new amplitude-frequency relationship from over 290.000 seismo-volcanic events at Stromboli during 2019–2020 which were detected by AWESAM. The module allows for a straightforward generalization and application to other volcanoes with frequent Strombolian activity worldwide. Furthermore, this module can be implemented for volcanoes with rarer explosions.

DetPoseNet: Improving Multi-Person Pose Estimation via Coarse-Pose Filtering.

Human detection and pose estimation are essential for understanding human activities in images and videos. Mainstream multi-human pose estimation methods take a top-down approach, where human detection is first performed, then each detected person bounding box is fed into a pose estimation network. This top-down approach suffers from the early commitment of initial detections in crowded scenes and other cases with ambiguities or occlusions, leading to pose estimation failures. We propose the DetPoseNet, an end-to-end multi-human detection and pose estimation framework in a unified three-stage network. Our method consists of a coarse-pose proposal extraction sub-net, a coarse-pose based proposal filtering module, and a multi-scale pose refinement sub-net. The coarse-pose proposal sub-net extracts whole-body bounding boxes and body keypoint proposals in a single shot. The coarse-pose filtering step based on the person and keypoint proposals can effectively rule out unlikely detections, thus improving subsequent processing. The pose refinement sub-net performs cascaded pose estimation on each refined proposal region. Multi-scale supervision and multi-scale regression are used in the pose refinement sub-net to simultaneously strengthen context feature learning. Structure-aware loss and keypoint masking are applied to further improve the pose refinement robustness. Our framework is flexible to accept most existing top-down pose estimators as the role of the pose refinement sub-net in our approach. Experiments on COCO and OCHuman datasets demonstrate the effectiveness of the proposed framework. The proposed method is computationally efficient (5-6x speedup) in estimating multi-person poses with refined bounding boxes in sub-seconds.

Phenology of Lycorma delicatula (Hemiptera: Fulgoridae) in Virginia, USA.

The spotted lanternfly, Lycorma delicatula (White), is an invasive planthopper that was first discovered in North America in Berks County, Pennsylvania in 2014. Currently, L. delicatula has spread to eight additional states and threatens agricultural, ornamental, and timber commodities throughout the United States. The timing of insect life events is very important in the development of pest management tools and strategies. In 2019 and 2020, L. delicatula phenology was successfully documented in Winchester, Virginia using weekly 5-min observational surveys at established monitoring plots. Each year, L. delicatula were active in the environment from May to November with initial detections of first, second, third, fourth, and adults occurring in May, May, June, June, and July, respectively. Cumulative average growing degree days were also calculated for the onset of each L. delicatula life stage using local weather data and a lower developmental threshold of 10°C. First-instar L. delicatula were initially observed at 135 and 111.5, adults at 835 and 887, and egg masses at 1673.5 and 1611.5 in 2019 and 2020, respectively. Combined, these data can be used by growers and land managers to facilitate timing of effective pest management strategies.

A high-resolution seismic catalog for the 2021 MS6.4/MW6.1 Yangbi earthquake sequence, Yunnan, China: Application of AI picker and matched filter

We present a high-resolution seismic catalog for the 2021 MS6.4/MW6.1 Yangbi sequence. The catalog has a time range of 2021-05-01 to 2021-05-28, and contains ~8,000 well located events. It captures the features of the whole foreshock sequence and the early aftershocks. We designed a detection strategy incorporating both an artificial intelligent (AI) picker and a matched filter algorithm. Here, we adopt a hybrid AI method incorporating convolutional and recurrent neural network (CNN & RNN) for event detection and phase picking respectively (i.e. CERP), a light-weight AI picker that can be trained with small volume of data. CERP is first trained with detections from a STA/LTA and Kurtosis-based method called PAL, and then construct a rather complete template set of ~4,000 events. Finally, the matched filter algorithm MESS augments the initial detections and measures differential travel times with cross-correlation, which finally results in precise relocation. This process gives 9,026 detections, among which 7,943 events can be well relocated. The catalog shows as expected power-law distribution of frequency magnitude and reveals detailed pattern of seismicity evolution. The main features are: (1) the foreshock sequence images simple fault geometry with consistent strike, but also show a variable event depth along strike; (2) the mainshock ruptures the same fault of the foreshock sequence and activate conjugate faults further to the southeast; (3) complex seismicity are developed in the post-seismic period, indicating complex triggering mechanisms. Thus, our catalog provides a reliable basis for further investigations, such as b-value studies, rupture process, and triggering relations.

Clinical Analysis of Improved Particle Swarm Algorithm-Based Magnetic Resonance Imaging Diagnosis of Placenta Accreta.

The magnetic resonance imaging (MRI) image processing capabilities were investigated based on the improved particle swarm optimization (IPSO) algorithm, and the clinical application analysis of MRI images in the diagnosis of placenta accreta (PA) was evaluated in this study. The MRI uterine images were detected on the basis of IPSO. Besides, the clinical data of 89 patients with PA were selected and collected, who were diagnosed by clinical cesarean section surgery and pathological comprehensive diagnosis in hospital from January 2018 to July 2020. Then, all of them underwent the ultrasound (US) and MRI examinations, and the differences of sensitivity, specificity, and accuracy between MRI and US under IPSO in the diagnosis of PA were compared, as well as the differences in the diagnosis of adhesive, implantable, and penetrated PA. The results showed that the difference in detection between IPSO-based MRI images and US images was not statistically substantial (p > 0.05), but the number of initial detections was higher than the number of US examination. MRI examination had higher sensitivity and specificity in the diagnosis of PA during pregnancy, especially for implantable PA, compared with US examination (p < 0.05). In conclusion, MRI images based on the improved particle swarm optimization algorithm showed a good application effect in the diagnosis of placental implantation diseases, which was worthy of further promotion in clinical practice.

Rapid Discovery and Detection of Haemaphysalis longicornis through the Use of Passive Surveillance and Collaboration: Building a State Tick-Surveillance Network.

Between March 2019 and February 2020, Asian long-horned ticks (Haemaphysalis longicornis Neumann, 1901) were discovered and collected for the first time in one middle and seven eastern Tennessee counties, facilitated by a newly developed passive and collaborative tick-surveillance network. Network collaborators included federal, state, county, university, and private resource personnel working with companion animals, livestock, and wildlife. Specimens were collected primarily from dogs and cattle, with initial detections of female adult stage ticks by stakeholders associated with parasitology positions (e.g., entomologists and veterinary parasitologists). Initial county tick detections were confirmed with morphological and molecular identifications, and then screened for the presence of animal-associated pathogens (Anaplasma marginale, Babesia species, Ehrlichia species, and Theileria orientalis), for which all tests were negative. Herein, we describe the identification and confirmation of these tick specimens as well as other results of the surveillance collaboration.

Breeding transients in capture\u2013recapture modeling and their consequences for local population dynamics

Standard procedures for capture–mark–recapture modelling (CMR) for the study of animal demography include running goodness-of-fit tests on a general starting model. A frequent reason for poor model fit is heterogeneity in local survival among individuals captured for the first time and those already captured or seen on previous occasions. This deviation is technically termed a transience effect. In specific cases, simple, uni-state CMR modeling showing transients may allow researchers to assess the role of these transients on population dynamics. Transient individuals nearly always have a lower local survival probability, which may appear for a number of reasons. In most cases, transients arise due to permanent dispersal, higher mortality, or a combination of both. In the case of higher mortality, transients may be symptomatic of a cost of first reproduction. A few studies working at large spatial scales actually show that transients more often correspond to survival costs of first reproduction rather than to permanent dispersal, bolstering the interpretation of transience as a measure of costs of reproduction, since initial detections are often associated with first breeding attempts. Regardless of their cause, the loss of transients from a local population should lower population growth rate. We review almost 1000 papers using CMR modeling and find that almost 40% of studies fitting the searching criteria (N = 115) detected transients. Nevertheless, few researchers have considered the ecological or evolutionary meaning of the transient phenomenon. Only three studies from the reviewed papers considered transients to be a cost of first reproduction. We also analyze a long-term individual monitoring dataset (1988–2012) on a long-lived bird to quantify transients, and we use a life table response experiment (LTRE) to measure the consequences of transients at a population level. As expected, population growth rate decreased when the environment became harsher while the proportion of transients increased. LTRE analysis showed that population growth can be substantially affected by changes in traits that are variable under environmental stochasticity and deterministic perturbations, such as recruitment, fecundity of experienced individuals, and transient probabilities. This occurred even though sensitivities and elasticities of these parameters were much lower than those for adult survival. The proportion of transients also increased with the strength of density-dependence. These results have implications for ecological and evolutionary studies and may stimulate other researchers to explore the ecological processes behind the occurrence of transients in capture–recapture studies. In population models, the inclusion of a specific state for transients may help to make more reliable predictions for endangered and harvested species.

Online multi-object tracking using KCF-based single-object tracker with occlusion analysis

Most state-of-the-art multiple-object tracking (MOT) methods adopt the tracking-by-detection (TBD) paradigm, which is a two-step procedure including the detection module and the tracking module. In these methods, the tracking performance heavily depends on initial detections and data association. In this paper, we present an online MOT method by introducing a single-object tracking (SOT) based on correlation filter. Our contributions lie in twofold: (a) we use the KCF-based SOT in learning of discriminative target appearance relying on handcrafted and deep features and (b) we employ the predicted result to refine the detection mistakes in a new way. Furthermore, we introduce normalize APCE score as an occlusion indicator of tracklet confidence, and build a candidate target hypotheses set to improve the association performance. Both approaches are found beneficial to eliminate the track errors caused by the inability of association algorithm. The experimental results, both qualitative and quantitative on three benchmark datasets, demonstrate that our tracking algorithm achieves comparable or even better results than competitor approaches.

Initial detections and spread of invasive Spodoptera frugiperda in China and comparisons with other noctuid larvae in cornfields using molecular techniques.

The fall armyworm, Spodoptera frugiperda, is a species native to the Americas and has spread to many countries in Africa and Asia in recent years. Proactive actions for potential invasion of S. frugiperda to China coordinated by government agencies and agricultural extension systems resulted in timely detection in January 2019 in Yunnan province neighboring onto Myanmar. The extensive monitoring in southern provinces of China since February 2019 resulted in dynamic tracking of S. frugiperda spreading to 13 provincial regions in China within 4 months by May 10, 2019, which is crucial for timely management actions in the fields. The first detections of S. frugiperda (corn strain) in China were confirmed using cytochrome oxidase subunit 1 (CO1) and triosephosphate isomerase (Tpi) genes molecular marker method. In addition to S. frugiperda, larvae of three other noctuid species with similar morphological appearance (S. litura, S. exigua and Mythimna separata) can occur simultaneously and cause similar damage in cornfields in southern China. Thus, we can use both morphological and molecular marker methods to compare larval stages of four noctuid species. Further, we discuss the risk of potential spread of invasive S. frugiperda to other regions and impact on corn production in China.

Multi-domain features for reducing false positives in automated detection of clustered microcalcifications in digital breast tomosynthesis.

In digital breast tomosynthesis (DBT) imaging, a microcalcification (MC) cluster may span across different slices and blurring exists in the out-of-focus slices. We developed a radiomics approach to extract features from focus slice and combine multiple spatial domains to reduce false positives (FPs) in an automated pipeline of detecting MC clusters. We performed a retrospective study on a cohort of 290 Chinese women patients with a total of 580 DBT volumes. We developed an automated MC detection pipeline that consists of two stages: an initial detection to identify a set of MC candidates that may include many FPs, followed by a radiomics-based classification model to identify and reduce the FPs. We extract both two-dimensional (2D) and three-dimensional (3D) radiomics features from multiple spatial domains, including a focus slice, projection image, and tomographic volume. A linear discriminant classifier was used coupled with a sequential forward feature selection procedure. The free-response operating characteristics (FROC) curve and partial area under the FROC curve (pAUC) in the FP rate range of 0 to 2 per DBT volume were used to evaluate the model's performance. At a sensitivity of 90%, the FP rate was reduced from 1.3 to 0.2 per DBT volume after applying the multi-domain-based classification on the initial detections. The multi-domain yielded a significantly higher pAUC compared to the initial detection (increase of pAUC=0.2278, P<0.0001), focus slice (increase of pAUC=0.0345, P=0.0152), project image (increase of pAUC=0.1043, P<0.0001), and tomographic volume (increase of pAUC=0.0791, P=0.0032). The radiomic features extracted from the three domains may provide complementary information and their integration can significantly reduce FPs in automated detection of MCs in DBT volumes on a large Chinese women population.

The dispersion-brightness relation for fast radio bursts from a wide-field survey.

Despite considerable efforts over the past decade, only 34 fast radio bursts-intense bursts of radio emission from beyond our Galaxy-have been reported1,2. Attempts to understand the population as a whole have been hindered by the highly heterogeneous nature of the searches, which have been conducted with telescopes of different sensitivities, at a range of radio frequencies, and in environments corrupted by different levels of radio-frequency interference from human activity. Searches have been further complicated by uncertain burst positions and brightnesses-a consequence of the transient nature of the sources and the poor angular resolution of the detecting instruments. The discovery of repeating bursts from one source3, and its subsequent localization4 to a dwarf galaxy at a distance of 3.7 billion light years, confirmed that the population of fast radio bursts is located at cosmological distances. However, the nature of the emission remains elusive. Here we report a well controlled, wide-field radio survey for these bursts. We found 20, none of which repeated during follow-up observations between 185-1,097hours after the initial detections. The sample includes both the nearest and the most energetic bursts detected so far. The survey demonstrates that there is a relationship between burst dispersionand brightness and thatthe high-fluence bursts are the nearby analogues of the more distant events found in higher-sensitivity, narrower-field surveys5.

A Limb-Based Graphical Model for Human Pose Estimation

Modeling the relationship among human joints is one of the most important components in human pose estimation. Most of previous methods define this relationship as a geometric constraint on the relative locations of two neighboring joints. In this constraint, the local appearance of the region connecting two neighboring joints is ignored. However, discarding this image appearance leads to some severe problems, such as double-counting and localization failure when the human pose is rare in the training dataset. Moreover, this image appearance, called human limb, plays an important role in human pose estimation in human visual system. Due to these reasons, we propose to solve a new task: human limb detection, which aims at detecting and representing this local image appearance. We combine this task with human joint localization as a unified framework. After getting the initial detections, we design a two-steps graphical model to capture the spatial relationship among human joints and limbs in a coarse to fine way. We evaluate the proposed method on two widely used datasets for human pose estimation: 1) frame labeled in cinema and 2) leeds sports pose datasets. The experiments results show the effectiveness of our method.

RECOVERING THE 3D POSE AND SHAPE OF VEHICLES FROM STEREO IMAGES

Abstract. The precise reconstruction and pose estimation of vehicles plays an important role, e.g. for autonomous driving. We tackle this problem on the basis of street level stereo images obtained from a moving vehicle. Starting from initial vehicle detections, we use a deformable vehicle shape prior learned from CAD vehicle data to fully reconstruct the vehicles in 3D and to recover their 3D pose and shape. To fit a deformable vehicle model to each detection by inferring the optimal parameters for pose and shape, we define an energy function leveraging reconstructed 3D data, image information, the vehicle model and derived scene knowledge. To minimise the energy function, we apply a robust model fitting procedure based on iterative Monte Carlo model particle sampling. We evaluate our approach using the object detection and orientation estimation benchmark of the KITTI dataset (Geiger et al., 2012). Our approach can deal with very coarse pose initialisations and we achieve encouraging results with up to 82 % correct pose estimations. Moreover, we are able to deliver very precise orientation estimation results with an average absolute error smaller than 4°.