Bias-Tunable Quantum Well Infrared Photodetector.

With the rapid advancement of Artificial Intelligence-driven object recognition, the development of cognitive tunable imaging sensors has become a critically important field. In this paper, we demonstrate an infrared (IR) sensor with spectral tunability controlled by the applied bias between the long-wave and mid-wave IR spectral regions. The sensor is a Quantum Well Infrared Photodetector (QWIP) containing asymmetrically doped double QWs where the external electric field alters the electron population in the wells and hence spectral responsivity. The design rules are obtained by calculating the electronic transition energies for symmetric and antisymmetric double-QW states using a Schrödinger-Poisson solver. The sensor is grown and characterized aiming detection in mid-wave (~5 µm) to long-wave IR (~8 µm) spectral ranges. The structure is grown using molecular beam epitaxy (MBE) and contains 25 periods of coupled double GaAs QWs and Al0.38Ga0.62As barriers. One of the QWs in the pair is modulation-doped to provide asymmetry in potential. The QWIPs are tested with blackbody radiation and FTIR down to 77 K. As a result, the ratio of the responsivities of the two bands at about 5.5 and 8 µm is controlled over an order of magnitude demonstrating tunability between MWIR and LWIR spectral regions. Separate experiments using parameterized image transformations of wideband LWIR imagery are performed to lay the framework for utilizing tunable QWIP sensors in object recognition applications.

Recurrent Convolutional Shape Regression.

The mainstream direction in face alignment is now dominated by cascaded regression methods. These methods start from an image with an initial shape and build a set of shape increments based on features with respect to the current estimated shape. These shape increments move the initial shape to the desired location. Despite the advantages of the cascaded methods, they all share two major limitations: (i) shape increments are learned independently from each other in a cascaded manner, (ii) the use of standard generic computer vision features such SIFT, HOG, does not allow these methods to learn problem-specific features. In this work, we propose a novel Recurrent Convolutional Shape Regression (RCSR) method that overcomes these limitations. We formulate the standard cascaded alignment problem as a recurrent process and learn all shape increments jointly, by using a recurrent neural network with a gated recurrent unit. Importantly, by combining a convolutional neural network with a recurrent one we avoid hand-crafted features, widely adopted in the literature and thus we allow the model to learn task-specific features. Besides, we employ the convolutional gated recurrent unit which takes as input the feature tensors instead of flattened feature vectors. Therefore, the spatial structure of the features can be better preserved in the memory of the recurrent neural network. Moreover, both the convolutional and the recurrent neural networks are learned jointly. Experimental evaluation shows that the proposed method has better performance than the state-of-the-art methods, and further supports the importance of learning a single end-to-end model for face alignment.

Viewpoint-Consistent 3D Face Alignment.

Most approaches to face alignment treat the face as a 2D object, which fails to represent depth variation and is vulnerable to loss of shape consistency when the face rotates along a 3D axis. Because faces commonly rotate three dimensionally, 2D approaches are vulnerable to significant error. 3D morphable models, employed as a second step in 2D+3D approaches are robust to face rotation but are computationally too expensive for many applications, yet their ability to maintain viewpoint consistency is unknown. We present an alternative approach that estimates 3D face landmarks in a single face image. The method uses a regression forest-based algorithm that adds a third dimension to the common cascade pipeline. 3D face landmarks are estimated directly, which avoids fitting a 3D morphable model. The proposed method achieves viewpoint consistency in a computationally efficient manner that is robust to 3D face rotation. To train and test our approach, we introduce the Multi-PIE Viewpoint Consistent database. In empirical tests, the proposed method achieved simple yet effective head pose estimation and viewpoint consistency on multiple measures relative to alternative approaches.