Towards an automatic road lane marks extraction based on ISODATA segmentation and shadow detection from large-scale aerial images

The automatic extraction of road features from remote sensed images has been a topic of great interest within the photogrammetric and remote sensing communities for over 3 decades. Although various techniques have been reported in the literature, it is still challenging to efficiently extract the road details with the increasing of image resolution as well as the requirement for accurate and up-to-date road data. In this paper, we will focus on the automatic detection of road lane markings, which are crucial for many applications, including lane level navigation and lane departure warning. The approach consists of four steps: i) data preprocessing, ii) image segmentation and road surface detection, iii) road lane marking extraction based on the generated road surface, and iv) testing and system evaluation. The proposed approach utilized the unsupervised ISODATA image segmentation algorithm, which segments the image into vegetation regions, and road surface based only on the Cb component of YCbCr color space. A shadow detection method based on YCbCr color space is also employed to detect and recover the shadows from the road surface casted by the vehicles and trees. Finally, the lane marking features are detected from the road surface using the histogram clustering. The experiments of applying the proposed method to the aerial imagery dataset of Gympie, Queensland demonstrate the efficiency of the approach.

Androgen levels increase by intratumoral de novo steroidogenesis during progression of castration-resistant prostate cancer

Although systemic androgen deprivation prolongs life in advanced prostate cancer, remissions are temporary because patients almost uniformly progress to a state of a castration-resistant prostate cancer (CRPC) as indicated by recurring PSA. This complex process of progression does not seem to be stochastic as the timing and phenotype are highly predictable, including the observation that most androgen-regulated genes are reactivated despite castrate levels of serum androgens. Recent evidence indicates that intraprostatic levels of androgens remain moderately high following systemic androgen deprivation therapy, whereas the androgen receptor (AR) remains functional, and silencing the AR expression following castration suppresses tumor growth and blocks the expression of genes known to be regulated by androgens. From these observations, we hypothesized that CRPC progression is not independent of androgen-driven activity and that androgens may be synthesized de novo in CRPC tumors leading to AR activation. Using the LNCaP xenograft model, we showed that tumor androgens increase during CRPC progression in correlation to PSA up-regulation. We show here that all enzymes necessary for androgen synthesis are expressed in prostate cancer tumors and some seem to be up-regulated during CRPC progression. Using an ex vivo radiotracing assays coupled to high-performance liquid chromatography-radiometric/mass spectrometry detection, we show that tumor explants isolated from CRPC progression are capable of de novo conversion of [(14)C]acetic acid to dihydrotestosterone and uptake of [(3)H]progesterone allows detection of the production of six other steroids upstream of dihydrotestosterone. This evidence suggests that de novo androgen synthesis may be a driving mechanism leading to CRPC progression following castration.

Facial feature detection for in-car environment

Acoustically, vehicles are extremely noisy environments and as a consequence audio-only in-car voice recognition systems perform very poorly. Seeing that the visual modality is immune to acoustic noise, using the visual lip information from the driver is seen as a viable strategy in circumventing this problem. However, implementing such an approach requires a system being able to accurately locate and track the driver’s face and facial features in real-time. In this paper we present such an approach using the Viola-Jones algorithm. Using this system, we present our results which show that using the Viola-Jones approach is a suitable method of locating and tracking the driver’s lips despite the visual variability of illumination and head pose.

Near infrared spectroscopy of stearic acid adsorbed on montmorillonite

The adsorption of stearic acid on both sodium montmorillonites and calcium montmorillonites has been studied by near infrared spectroscopy complimented with infrared spectroscopy. Upon adsorption of stearic acid on Ca-Mt additional near infrared bands are observed at 8236 cm-1 and is assigned to an interaction of stearic acid with the water of hydration. Upon adsorption of the stearic acid on Na-Mt, the NIR bands are now observed at 5671, 5778, 5848 and 5912 cm-1 and are assigned to the overtone and combination bands of the CH fundamentals. Additional bands at 4177, 4250, 4324, 4337, 4689 and 4809 cm-1 are attributed to CH combination bands resulting from the adsorption of the stearic acid. Stearic acid is used as a model molecule for adsorption studies. The application of near infrared spectroscopy to the study of this adsorption proved most useful.