To simulate the evacuation behaviors of different people in abnormal traffic accidents, a new database, i.e., the video database of evacuation behaviors in abnormal traffic accidents is established by showing subjects videos with traffic accident images to simulate abnormal traffic accidents in a laboratory setting. The database includes non-evacuation behavior videos and evacuation behavior videos of 200 subjects, as well as the statistical results of survey inventories for these 200 subjects. The survey inventories include the State Anxiety Inventory(SAI), the State-Trait Anxiety Inventory (STAI), the Beck Depression Inventory (BDI), the Big Five Inventory (BFI), and an affective inventory corresponding to the experimental videos. This database should help develop effective algorithms to compare the evacuation behaviors of different people and suggest effective methods to deal with emergencies such as fires, explosions, and car accidents.
Near-infrared (NIR) face recognition (FR) has demonstrated robustness against changes in ambient illumination, which makes it suitable for surveillance even under weak illumination conditions. However, the existing database for NIR FR only contains frontal face images, and the impact of pose variation on the robustness of NIR FR remains unascertained. We developed an NIR face database with 57 pose variations in a dark environment, which can be used in pose-invariant FR research. Convolutional neural networks (CNNs) were designed and tested in comparison to the traditional method in the database. The experimental results showed that a difference of even 10 deg between the gallery and testing sets can dramatically reduce the recognition performance. Additionally, an average accuracy of 90.58% was obtained for pose-invariant recognition by employing more pose variations in the gallery set using the CNN-based method.
A major problem for obtaining target reflectance via hyperspectral imaging systems is the presence of illumination and shadow effects. These factors are common artefacts, especially when dealing with a hyperspectral imaging system that has sensors in the visible to near infrared region. This region is known to have highly scattered and diffuse radiance that can modify the energy recorded by the imaging system. A shadow effect will lower the target reflectance values due to the small radiant energy impinging on the target surface. Combined with illumination artefacts, such as diffuse scattering from the surrounding targets, background or environment, the shape of the shadowed target reflectance will be altered. We propose a new method to compensate for illumination and shadow effects on hyperspectral imageries by using a polarization technique. This technique, called spectro-polarimetry, estimates the direct and diffuse irradiance based on two images taken with and without a polarizer. The method is then evaluated using a spectral similarity measure, angle and distance metric. The results of indoor and outdoor tests have shown that using the spectro-polarimetry technique can improve the spectral constancy between shadow and full illumination spectra.
People tracking in crowded scene have been a popular, and at the same time a very difficult topic in computer vision. It
is mainly because of the difficulty for the acquisition of intrinsic signatures of targets from a single view of the scene.
Many factors, such as variable illumination conditions and viewing angles, will induce illusive modification of intrinsic
signatures of targets. The objective of this paper is to verify if colour constancy (CC) approach really helps people
tracking in CCTV network system. We have testified a number of CC algorithms together with various colour
descriptors, to assess the efficiencies of people recognitions from multi-camera i-LIDS data set via receiver operation
characteristics (ROC). It is found that when CC is applied together with some form of colour restoration mechanisms
such as colour transfer, it does improve people recognition by at least a factor of 2. An elementary luminance based CC
coupled with a pixel based colour transfer algorithm have been developed and it is reported in this paper.
This paper reports on the enhancement of biologically-inspired machine vision through a rotation invariance mechanism.
Research over the years has suggested that rotation invariance is one of the fundamental generic elements of object
constancy, a known generic visual ability of the human brain.
Cortex-like vision unlike conventional pixel based
machine vision is achieved by mimicking neuromorphic mechanisms of the primates' brain. In this preliminary study,
rotation invariance is implemented through histograms from Gabor features of an object. The performance of rotation
invariance in the neuromorphic algorithm is assessed by the classification accuracies of a test data set which consists of
image objects in five different orientations. It is found that a much more consistent classification result over these five
different oriented data sets has been achieved by the integrated rotation invariance neuromorphic algorithm compared to
the one without. In addition, the issue of varying aspect ratios of input images to these models is also addressed, in an
attempt to create a robust algorithm against a wider variability of input data. The extension of the present achievement is
to improve the recognition accuracies while incorporating it to a series of different real-world scenarios which would
challenge the approach accordingly.
Hyperspectral imaging (HSI) systems have been used widely in many applications including the defence and military for
target acquisitions. However, the effectiveness of HSI can be greatly hampered by illumination artifacts such as
shadowing or bidirectional reflection differentials issues. This paper addresses how shadows in the HSI, particularly for
the imageries that are taken in the indoor scenarios, can be partially mitigated through a diffused irradiance
compensation (DIC) methodology. The effectiveness of the proposed work is then compared with the widely adopted
pixel normalisation and band ratioing methods. The performances of all these processing methods have been assessed
using Maximum Likelihood Classifier. The result has shown an almost 70% improvement in classification accuracy after
the raw DN data is translated into 'apparent' reflectance using simple ELM based method, and the classification
accuracy after spectral normalisation is ~26% worse than without normalization. When the proposed diffused irradiance
compensation (DIC) is combined with other band ratioing techniques, the classification accuracy is found to be improved
by ~7% over that processed by the ELM method for the entire scene. There are about 32% of shadowed pixels in this
data set and hence 7% of improvement represents a significant improvement on the shadow mitigation.
Emotional or physical stresses induce a surge of adrenaline in the blood stream under the command of the sympathetic
nerve system, which, cannot be suppressed by training. The onset of this alleviated level of adrenaline triggers a number
of physiological chain reactions in the body, such as dilation of pupil and an increased feed of blood to muscles etc. This
paper reports for the first time how Electro-Optics (EO) technologies such as hyperspectral [1,2] and thermal imaging[3]
methods can be used for the detection of stress remotely. Preliminary result using hyperspectral imaging technique has
shown a positive identification of stress through an elevation of haemoglobin oxygenation saturation level in the facial
region, and the effect is seen more prominently for the physical stressor than the emotional one. However, all results
presented so far in this work have been interpreted together with the base line information as the reference point, and that
really has limited the overall usefulness of the developing technology. The present result has highlighted this drawback
and it prompts for the need of a quantitative assessment of the oxygenation saturation and to correlate it directly with the
stress level as the top priority of the next stage of research.
This paper reports how Electro-Optics (EO) technologies such as thermal and hyperspectral [1-3] imaging methods can
be used for the detection of stress remotely. Emotional or physical stresses induce a surge of adrenaline in the blood
stream under the command of the sympathetic nerve system, which, cannot be suppressed by training. The onset of this
alleviated level of adrenaline triggers a number of physiological chain reactions in the body, such as dilation of pupil and
an increased feed of blood to muscles etc. The capture of physiological responses, specifically the increase of blood
volume to pupil, have been reported by Pavlidis's pioneer thermal imaging work [4-7] who has shown a remarkable
increase of skin temperature in the periorbital region at the onset of stress. Our data has shown that other areas such as
the forehead, neck and cheek also exhibit alleviated skin temperatures dependent on the types of stressors. Our result has
also observed very similar thermal patterns due to physical exercising, to the one that induced by other physical stressors,
apparently in contradiction to Pavlidis's work [8]. Furthermore, we have found patches of alleviated temperature regions
in the forehead forming patterns characteristic to the types of stressors, dependent on whether they are physical or
emotional in origin. These stress induced thermal patterns have been seen to be quite distinct to the one resulting from
having high fever.
This paper reports how objects in street scenes, such as pedestrians and cars, can be spotted, recognised and then
subsequently tracked in cluttered background using a cortex like vision approach. Unlike the conventional pixel based
machine vision, tracking is achieved by recognition of the target implemented in neuromorphic ways. In this preliminary
study the region of interest (ROI) of the image is spotted according to the salience and relevance of the scene and
subsequently target recognition and tracking of the object in the ROI have been performed using a mixture of feed
forward cortex like neuromorphic algorithms together with statistical classifier & tracker. Object recognitions for four
categories (bike, people, car & background) using only one set of ventral visual like features have achieved a max of
~70% accuracy and the present system is quite effective for tracking prominent objects relatively independent of
background types. The extension of the present achievement to improve the recognition accuracy as well as the
identification of occluded objects from a crowd formulates the next stage of work.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.