* 同步esp-video组件驱动摄像头的配置
* 修改Waveshare ESP32-S3-AUDIO-Board 摄像头配置。
* Modify the XCLK parameters of the camera, and modify the config.txt to be compatible with 2640 and 5640.
* Update the esp_video component version to 1.3.0
* Downgrade the esp_video component version. There are unfixed bugs.
* Update component version
* feat: Wake up when a person is detected
* fix: Solve the problem of no sound when using WakeWordInvoke
* fix: Solve the problem of triggering dialogue when the person has not left
* feat(vision): 优化视觉检测逻辑并增加配置接口
本次提交旨在优化视觉检测功能,使其行为更自然、更智能,并为用户提供灵活的配置选项。
主要更新包括:
1. 引入了更精细的检测状态机:
- IDLE: 空闲状态,等待检测目标。
- VALIDATING: 验证状态,在检测到目标后,持续一段时间(可配置)以确认其存在,防止误触发。
- COOLDOWN: 冷却状态,在一次成功交互后进入,避免过于频繁的打扰。
2. 新增了用于配置视觉检测的 MCP 工具:
- self.vision.get_detection_config: 获取当前的检测参数(阈值、冷却间隔、验证时长、目标类型)。
- self.vision.set_detection_config: 允许用户动态修改这些参数,以适应不同场景。
3. 性能优化:
- 增加了配置参数的内存缓存,避免了在检测循环中对 NVS 的频繁访问。
* feat: Inference using Model 4
* feat: default inference disable
* feat: version cmd change to output json
* fix: fix image display
* Fix include directives for esp_check and esp_app_desc
---------
Co-authored-by: Spencer <love4yzp@gmail.com>
Co-authored-by: Xiaoxia <terrence@tenclass.com>
* refactor: migrate camera module to esp-video library
* refactor: migrate boards to esp-video API (1/2)
* refactor: migrate boards to esp-video API (2/2)
* fix: use ESP-IDF 5.5
* refactor: migrate the JPEG encoder to `esp_new_jpeg`
* feat: add YUV422 support
* feat: improve pixelformat and device selection process
* feat: use ESP32-P4 Hardware JPEG Encoder
* add support for Wireless-Tag WTP4C5MP07S ESP32P4 + 7 inch MIPI DSI LCD display combo
* a minor update of README
* update of the device name/folder
* exclude USE_DEVICE_AEC from the options list
* Adapt for LilyGO-T-Circle-S3 device
* Adapt for LilyGO-T-Circle-S3 device
* Remove comments and modify the size of the lilygo-t-circle-s3 image
* Modify the code style and format to Google C++
* Modify the code style and format to Google C++
* Fixed bugs in the LILYGO T-Circle-S3 board and added support for two new boards: LILYGO T-Display-S3-Pro-MVSRLora and LILYGO T-Display-S3-Pro-MVSRLora_NO_BATTERY.
* Added support for two new boards: LILYGO T-Display-S3-Pro-MVSRLora and LILYGO T-Display-S3-Pro-MVSRLora_NO_BATTERY.
* Merge branch 'main' of https://github.com/Llgok/xiaozhi-esp32
* Added support for two new boards: LILYGO T-Display-S3-Pro-MVSRLora and LILYGO T-Display-S3-Pro-MVSRLora_NO_BATTERY.
* Added support for two new boards: LILYGO T-Display-S3-Pro-MVSRLora and LILYGO T-Display-S3-Pro-MVSRLora_NO_BATTERY.
* Added support for two new boards: LILYGO T-Display-S3-Pro-MVSRLora and LILYGO T-Display-S3-Pro-MVSRLora_NO_BATTERY.
* Added support for two new boards: LILYGO T-Display-S3-Pro-MVSRLora and LILYGO T-Display-S3-Pro-MVSRLora_NO_BATTERY.
* Fix the color display issue for T-Display-S3-Pro-MVSRLora and LILYGO T-Display-S3-Pro-MVSRLora_NO_BATTERY.
* Update T-CameraPlus-S3_V1.2 Version Xiaozhi Example
* Resolve the issue where the camera on the T-CameraPlus-S3_V1.2 board cannot be used normally.
* Enhance microphone reception volume
* fix the issue where voice wake-up is not working
* fix the issue where voice wake-up is not working
* Add LILYGO T-Display-P4 board adaptation
* Modify the MIPILCDDISPLAY class
* Added Waveshare ESP32-P4-WIFI6-Touch-LCD-7B third party board
* Add config,json for Waveshare ESP32-P4 series boards
* Fix some errors
* update v2 partition table readme
* feat: Add user only tool
* Add image cache
* smaller cache and buffer, more heap
* use MAIN_EVENT_CLOCK_TICK to avoid audio glitches
* fix: esp_psram_get_size not found in c3
* Bump to 1.9.0
* fix: resolve crash when closing codec dev on esp-hi
* fix: fix incorrect status display in non-zh-CN languages
* fix: reduce noise when not in Speaking state
