The automatic detection of pedestrian heads in crowded environments is essential for crowd analysis and management tasks, particularly in high-risk settings such as railway platforms and event entrances. These environments, characterized by dense crowds and dynamic movements, are underrepresented in public datasets, posing challenges for existing deep learning models. To address this gap, we introduce the Railway Platforms and Event Entrances-Heads (RPEE-Heads) dataset, a novel, diverse, high-resolution, and accurately annotated resource. It includes 109,913 annotated pedestrian heads across 1,886 images from 66 video recordings, with an average of 56.2 heads per image. Annotations include bounding boxes for visible head regions. In addition to introducing the RPEE-Heads dataset, this paper evaluates eight state-of-the-art object detection algorithms using the RPEE-Heads dataset and analyzes the impact of head size on detection accuracy. The experimental results show that You Only Look Once v9 and Real-Time Detection Transformer outperform the other algorithms, achieving mean average precisions of 90.7% and 90.8%, with inference times of 11 and 14 milliseconds, respectively. Moreover, the findings underscore the need for specialized datasets like RPEE-Heads for training and evaluating accurate models for head detection in railway platforms and event entrances. The dataset and pretrained models are available at https://doi.org/10.34735/ped.2024.2.

With the advent of novel cancer treatment options such as immunotherapy, studying the tumour immune micro-environment is crucial to inform on prognosis and understand response to therapeutic agents. A key approach to characterising the tumour immune micro-environment may be through combining (1) digitised microscopic high-resolution optical images of hematoxylin and eosin (H&E) stained tissue sections obtained in routine histopathology examinations with (2) automated immune cell detection and classification methods. However, current individual immune cell classification models for digital pathology present relatively poor performance. This is mainly due to the limited size of currently available datasets of individual immune cells, a consequence of the time-consuming and difficult problem of manually annotating immune cells on digitised H&E whole slide images. In that context, we introduce Immunocto, a massive, multi-million automatically generated database of 6,848,454 human cells, including 2,282,818 immune cells distributed across 4 subtypes: CD4$^+$ T cell lymphocytes, CD8$^+$ T cell lymphocytes, B cell lymphocytes, and macrophages. For each cell, we provide a 64$\times$64 pixels H&E image at $\mathbf{40}\times$ magnification, along with a binary mask of the nucleus and a label. To create Immunocto, we combined open-source models and data to automatically generate the majority of contours and labels. The cells are obtained from a matched H&E and immunofluorescence colorectal dataset from the Orion platform, while contours are obtained using the Segment Anything Model. A classifier trained on H&E images from Immunocto produces an average F1 score of 0.74 to differentiate the 4 immune cell subtypes and other cells. Immunocto can be downloaded at: https://zenodo.org/uploads/11073373.

There are now two ways of creating digital images with a camera. You can either follow a software-centric computational photography approach. The other way is to stick to traditional hardware-centric optical photography. The former is used with AI to help enhance the final image, the latter relies on the quality of the camera's components (e.g. The two techniques may differ, but they are not at all on a collision course.

Though it's possible our readers haven't heard much about artificial intelligence, you'd have to be living under a rock if you've never heard of'the cloud,' let alone how rare it would be if you had never interacted with one. Both of these concepts can be so far removed from the average user's daily life. Yet some of the more modern telephones carry technology inside them that enables some of the most basic artificial intelligence. Almost all Android and Apple powered phones, by comparison, keep our settings, backups, photos, and all sorts of information synchronized to one or multiple cloud services. When I write about artificial intelligence, I have to acknowledge the major players at the moment are Intel, IBM, and Google. Likewise, when bringing up cloud service providers, Google comes up again, along with Apple, Microsoft, and Amazon Web Services.

One of the benefits of investing in a new flagship handset such as the Pixel 4, is that it gives you access to exclusive apps and features. Just as the likes of Samsung and OnePlus do, Google gives owners of its latest Pixel devices new toys to play with, and with the Pixel 4 this included the Recorder app. More than just a simple audio recording tool, Recorder also uses AI and voice recognition to automatically transcribe and label recordings in real time to make them far more useful. Now there's good news for anyone packing a Pixel 2, Pixel 3 or Pixel 3a: the Recorder app is no longer exclusive to the Pixel 4. The automatic transcription offered by the Recorder app is great for taking minutes of meetings, dictating documents and much more. The app is now being opened up to a wider range of users, giving many more people the chance to avoid the laborious task of transcribing recordings by hand. It's not great news for everyone, as the app remains exclusive to Google's own Pixel devices, but it's no longer just the Pixel 4. Strangely, Google did not initially make a great fuss about expanding the availability of Recorder but after it was spotted by numerous users, the company went on to confirm things on Twitter: As the tweet notes, transcription is only available in English, and it's not clear if Google plans to expand into other languages.

We recently ended our week-long investigation into How We Reproduce--or, as it turns out, how we don't. In addition to covering a few forms of contraception in our fertility and pregnancy gear roundup, we also took a look at advances in male contraception and gleefully childfree forums. The good news is that if you're not spending money on baby bottles and strollers, then you have plenty left in your pocket for Dell's March Madness sale. If you've been looking for an affordable smart speaker, Amazon's Echo and Fire Tablet sale ends today. We also have a few other great bargains on some of our favorite action camera, smart TVs, and more.

Google's latest flagship smartphones -- the Pixel 3 and Pixel 3 XL -- are finally shipping to customers, and the reviews are unanimous: The rear camera and dual selfie cams are best in class. But as good as those cameras might be, they're a bit puzzling -- and sort of paradoxical. The original Pixel and Pixel XL have two cameras: one front and one rear. The Pixel 2 and Pixel 2 XL have two cameras: one front and one rear. And the Pixel 3 and Pixel 3 XL have three cameras: two front and one rear.

Google debuted the Pixel 3 and Pixel 3 XL with dual front-facing cameras and glass body last week, and while there are notable hardware improvements, it's things like being able to screen calls with your own conversational AI or make reservations with Duplex that make the latest Pixel stand out. Many of the Pixel 3 and Pixel 3 XL's best features, whether it's a predictive battery or a camera with Portrait Mode that scans business cards and helps you choose your best pictures, are made better with AI. Pixel 3 phones start shipping Thursday. The Pixel 3 and Pixel 3 XL are the first in Google's Pixel series to ditch aluminum for glass, which enables support for wireless charging -- also a first. It's a bit deceptive; the bottom portion of the rear cover has a matte coating, giving them the two-tone aesthetic characteristic of their predecessors.

The Pixel 2 had arguably the best smartphone camera on the market, and Google wants to make sure it stays that way. During its Pixel unveiling today, it introduced a raft of new camera features for the Pixel 3 and Pixel 3XL smartphones, including an improved zoom, wider-angle camera, smile and blink detection, bokeh control and more -- all with just a single lens on the back. The quality is apparently good enough for Terrence Malick, who shot a video that was featured at the event, so it might be good enough for the rest of us, too. Some of the features are enabled with the fresh hardware, to be sure. There's a brand new 12.2-megapixel sensor on the back, with a sharper wide-angle lens to allow for zooming.

Google's new Pixel 3 smartphones attempt to push the computational photography envelope, challenging Apple's new iPhone XS and Samsung's Galaxy S9. As with last year's Pixel 2, Google is further flexing its artificial-intelligence muscle, with more and more local AI-driven features across every facet of the device, from the camera and smart Gmail replies to battery life and device control. "We've been very thoughtful about how we design phones, thinking about their purpose for consumers," said Mario Queiroz, head of Google's Pixel. "We want to make sure we have a the right balance between being really helpful but not intrusive, being delightful but not controlling, simple but not cumbersome." The Pixel devices look familiar on the outside, with a two-tone back that is now all glass with two finishes – polished at the top and etched at the bottom.