Abstract-Accurate, robust, inexpensive gaze tracking in the car can help keep a driver safe by facilitating the more effective study of how to improve (1) vehicle interfaces and (2) the design of future Advanced Driver Assistance Systems. In this paper, we estimate head pose and eye pose from monocular video using methods developed extensively in prior work and ask two new interesting questions. First, how much better can we classify driver gaze using head and eye pose versus just using head pose? Second, are there individual-specific gaze strategies that strongly correlate with how much gaze classification improves with the addition of eye pose information? We answer these questions by evaluating data drawn from an on-road study of 40 drivers. The main insight of the paper is conveyed through the analogy of an "owl" and "lizard" which describes the degree to which the eyes and the head move when shifting gaze. When the head moves a lot ("owl"), not much classification improvement is attained by estimating eye pose on top of head pose. On the other hand, when the head stays still and only the eyes move ("lizard"), classification accuracy increases significantly from adding in eye pose. We characterize how that accuracy varies between people, gaze strategies, and gaze regions.

Automated estimation of the allocation of a driver's visual attention may be a critical component of future Advanced Driver Assistance Systems. In theory, vision-based tracking of the eye can provide a good estimate of gaze location. In practice, eye tracking from video is challenging because of sunglasses, eyeglass reflections, lighting conditions, occlusions, motion blur, and other factors. Estimation of head pose, on the other hand, is robust to many of these effects, but cannot provide as fine-grained of a resolution in localizing the gaze. However, for the purpose of keeping the driver safe, it is sufficient to partition gaze into regions. In this effort, we propose a system that extracts facial features and classifies their spatial configuration into six regions in real-time. Our proposed method achieves an average accuracy of 91.4% at an average decision rate of 11 Hz on a dataset of 50 drivers from an on-road study.

Mutation in myostatin (MSTN), a negative regulator of muscle growth in skeletal muscle, resulted in increased muscle mass in mammals and fishes. However, MSTN mutation in avian species has not been reported. The objective of this study was to generate MSTN mutation in quail and investigate the effect of MSTN mutation in avian muscle growth. Recently, a new targeted gene knockout approach for the avian species has been developed using an adenoviral CRISPR/Cas9 system. By injecting the recombinant adenovirus containing CRISPR/Cas9 into the quail blastoderm, potential germline chimeras were generated and offspring with three base-pair deletion in the targeted region of the MSTN gene was identified. This non-frameshift mutation in MSTN resulted in deletion of cysteine 42 in the MSTN propeptide region and homozygous mutant quail showed significantly increased body weight and muscle mass with muscle hyperplasia compared to heterozygous mutant and wild-type quail. In addition, decreased fat pad weight and increased heart weight were observed in MSTN mutant quail in an age- and sex-dependent manner, respectively. Taken together, these data indicate anti-myogenic function of MSTN in the avian species and the importance of cysteine 42 in regulating MSTN function.

Zygotes at the 1-cell stage have been genetically modified by microinjecting the CRISPR/Cas9 components for the generation of targeted gene knockout in mammals. In the avian species, genetic modification of the zygote is difficult because its unique reproductive system limits the accessibility of the zygote at the 1-cell stage. To date, only a few CRISPR/Cas9-mediated gene knockouts have been reported using the chicken as a model among avian species, which requires 3 major processes: isolation and culture of primordial germ cells (PGCs), modification of the genome of PGCs in vitro, and injection of the PGCs into the extraembryonic blood vessel at the early embryonic stages when endogenous PGCs migrate through circulation to the genital ridge. In the present study, the adenoviral CRISPR/Cas9 vector was directly injected into the quail blastoderm in newly laid eggs. The resulting chimeras generated offspring with targeted mutations in the melanophilin (MLPH) gene, which is involved in melanosome transportation and feather pigmentation. MLPH homozygous mutant quail exhibited gray plumage, whereas MLPH heterozygous mutants and wild-type quail exhibited dark brown plumage. In addition, the adenoviral vector was not integrated into the genome of knockout quail, and no mutations were detected in potential off-target regions. This method of generating genome-edited poultry is expected to accelerate avian research and has potential applications for developing superior genetic lines for poultry production in the industry.

This work may have important implications for attention management in the context of the increasing prevalence of in-vehicle demands as well as of vehicle automation.